© 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. 217203
    Prev
    Next
    INDEX
    Explanations

    increase, decrease, working, winner, encrypt, trucks

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

    percentage increases and growth

    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
    О
    0.46
    $>$
    0.45
    $',
    0.42
    <0xA8>
    0.41
    $+
    0.41
    +\
    0.40
    September
    0.40
    Uc
    0.40
     pollution
    0.39
     +\
    0.39
    POSITIVE LOGITS
     Persever
    0.52
     prépar
    0.49
    ர்கள்
    0.48
     professionnel
    0.47
     persever
    0.47
    কারীদের
    0.47
    နိုင်ငံ
    0.47
     Inns
    0.46
    蔼
    0.46
    SampleSize
    0.46
    Activations Density 0.000%

    No Known Activations