© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 108948
    Prev
    Next
    INDEX
    Explanations

    Field Office

    np_acts-logits-general · gemini-2.5-flash-lite

    The neuron is looking for informal, first‐person–style, how-to or “DIY” discussion posts (e.g. car-mod and hardware-advice threads) rather than formal technical/spec or code/legal/biochemistry write-ups.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    }");
    -1.02
     atlet
    -1.00
    }")
    -0.99
     sosis
    -0.95
    paddingTop
    -0.94
    ulemon
    -0.94
    }')
    -0.93
     oscu
    -0.89
    ㄅ
    -0.88
    orkshire
    -0.88
    POSITIVE LOGITS
    ウマ
    0.97
    uresti
    0.94
    ↵↵↵↵↵↵↵↵↵↵↵↵
    0.88
    サイ
    0.87
    athies
    0.87
    шед
    0.86
    atorship
    0.86
    ↵↵↵↵↵↵
    0.86
     Masson
    0.86
    trums
    0.85
    Activations Density 0.003%

    No Known Activations