© 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
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 107805
    Prev
    Next
    INDEX
    Explanations

    specific names and compounds

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

    code comments and documentation blocks in programming files.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    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
     ニ
    -0.76
     apparently
    -0.76
     percor
    -0.75
    ۰
    -0.75
    VALIDATE
    -0.72
    着
    -0.72
     уточ
    -0.72
    ]);
    -0.72
    hatic
    -0.71
    tedly
    -0.70
    POSITIVE LOGITS
     dates
    0.86
     Josie
    0.84
    𓂃
    0.83
     matchups
    0.82
     reagieren
    0.81
    утбо
    0.80
    σαι
    0.80
    ₜ
    0.79
    ські
    0.79
     Sita
    0.79
    Activations Density 0.008%

    No Known Activations