© 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. 160162
    Prev
    Next
    INDEX
    Explanations

    automation, bot, attacks

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

    though that is part

    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
     налази
    0.53
    겔
    0.48
     эфи
    0.45
    ່າຍ
    0.45
    に限
    0.45
     সান
    0.45
    <0x91>
    0.45
    asiti
    0.45
    楧
    0.45
    igal
    0.44
    POSITIVE LOGITS
     हमले
    0.56
     използ
    0.47
    ത്തിലൂടെ
    0.46
    automation
    0.45
     कलेक्टर
    0.44
     później
    0.44
     मैकेन
    0.43
     onslaught
    0.42
     automation
    0.42
    bot
    0.41
    Activations Density 0.000%

    No Known Activations