© 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. 33275
    Prev
    Next
    INDEX
    Explanations

    heaven and hell

    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
    羕
    -2.45
    
    -2.42
    콴
    -2.20
    “
    -2.17
    鉭
    -2.14
     dasarnya
    -2.09
     nostre
    -2.08
     può
    -2.06
    ؎
    -2.03
    綃
    -2.02
    POSITIVE LOGITS
    .
    2.58
     otras
    2.56
     {}));
    2.28
    <bos>
    2.23
    ский
    2.17
    {
    2.08
    ⟞
    2.05
     новая
    2.02
     другие
    2.02
     "
    2.02
    Activations Density 0.008%

    No Known Activations