© 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. 154492
    Prev
    Next
    INDEX
    Explanations

    JCB Vertical Lifter

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

    body, advancement, excitements

    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
    setTime
    0.48
    <0xC9>
    0.46
    買う
    0.45
    کم
    0.43
    ቈ
    0.43
    ಘ
    0.42
    logram
    0.42
    غول
    0.42
    pov
    0.42
    レストラン
    0.41
    POSITIVE LOGITS
     advancements
    0.55
     bodys
    0.52
    的全
    0.48
     transmutation
    0.47
    রাষ্ট
    0.45
    పంచ
    0.44
     Existem
    0.44
     aberrations
    0.43
    阱
    0.43
     trypt
    0.43
    Activations Density 0.003%

    No Known Activations