© 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. 65131
    Prev
    Next
    INDEX
    Explanations

    superscript citation markers

    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
     in
    -2.09
    胧
    -1.80
    就连
    -1.74
     for
    -1.72
    StoryboardSegue
    -1.71
    zembro
    -1.65
    体は
    -1.64
     around
    -1.63
    !’
    -1.63
    ’:
    -1.62
    POSITIVE LOGITS
     '
    2.05
     bekom
    1.66
    "
    1.64
    {
    1.59
     konkrete
    1.58
     neón
    1.57
     praktische
    1.55
     rivales
    1.53
    ᴘ
    1.52
    </em>
    1.49
    Activations Density 0.016%

    No Known Activations