© 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. 95401
    Prev
    Next
    INDEX
    Explanations

    those that work

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

    Ponzi schemes, intently, component analysis

    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
    COMPANY
    0.51
    STRING
    0.49
    LONG
    0.48
    ():
    0.47
    January
    0.46
     여섯
    0.44
     ہے۔
    0.44
    COMB
    0.44
    ⑨
    0.44
    TTS
    0.43
    POSITIVE LOGITS
    t
    0.60
     and
    0.52
    rl
    0.50
    ân
    0.47
    re
    0.47
    ul
    0.47
    idium
    0.47
    essa
    0.47
    anç
    0.47
    sama
    0.47
    Activations Density 0.000%

    No Known Activations