© 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. 22-GEMMASCOPE-RES-131K
    7. 25649
    Prev
    Next
    INDEX
    Explanations

    meal

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    plash
    -2.41
    ቍ
    -2.17
    ൩
    -2.14
    thereum
    -2.09
    т
    -2.09
    ႂ
    -2.06
    ))
    -2.05
    ientras
    -1.99
    鉍
    -1.98
    昞
    -1.98
    POSITIVE LOGITS
    al
    2.25
    time
    2.16
     The
    2.16
    mu
    2.13
    ll
    2.09
                
    2.09
     But
    2.09
    ться
    2.09
    .
    2.08
    ra
    2.03
    Activations Density 0.003%

    No Known Activations