© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 14696
    Prev
    Next
    INDEX
    Explanations

    biggest lesson

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

    **Names** and titles

    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
     Mes
    0.49
    خ
    0.45
     Hoch
    0.44
    何时
    0.42
     Crist
    0.42
    وك
    0.41
     Analyse
    0.40
     مه
    0.40
    動画
    0.40
    𝘣
    0.40
    POSITIVE LOGITS
     darkened
    0.50
     urination
    0.50
     waisted
    0.49
     darkening
    0.49
     toasted
    0.48
     slowed
    0.47
     cooled
    0.46
     prickly
    0.46
     stronghold
    0.45
     spongy
    0.45
    Activations Density 0.000%

    No Known Activations