© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 154148
    Prev
    Next
    INDEX
    Explanations

    groups of, write me, we ought

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

    Elden Ring

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    })^{
    0.55
    ört
    0.52
    Kub
    0.48
     हेलो
    0.48
     章
    0.48
    ల
    0.48
     Иванов
    0.47
    }).
    0.46
     推
    0.45
    })$.
    0.45
    POSITIVE LOGITS
    寄り
    0.45
    ثمان
    0.45
     dettaglio
    0.45
     energia
    0.45
     artisanal
    0.45
    懟
    0.45
    ым
    0.44
     Mejor
    0.43
    自家
    0.43
     energi
    0.42
    Activations Density 0.001%

    No Known Activations