© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 2972
    Prev
    Next
    INDEX
    Explanations

    draw or till

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

    draw or writing actions

    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_53_width_65k_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
     rehearsal
    0.47
     প্রি
    0.41
     trembled
    0.40
    ድን
    0.40
     rehears
    0.40
    striped
    0.39
     Guten
    0.39
    𒊒
    0.38
     inscribed
    0.37
     tenement
    0.37
    POSITIVE LOGITS
     Draw
    0.48
     Withdraw
    0.47
     Draws
    0.46
    Draw
    0.44
     vil
    0.44
     withdraw
    0.43
     DRAW
    0.43
    withdrawal
    0.43
     Bat
    0.42
    Withdraw
    0.42
    Activations Density 0.000%

    No Known Activations