© 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. 91904
    Prev
    Next
    INDEX
    Explanations

    fake it till you make it

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

    account data EM debt

    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
     raiding
    0.52
    с
    0.48
     sacking
    0.45
    ссий
    0.45
    ೈನ
    0.44
     inland
    0.44
     relaunch
    0.44
     myopia
    0.43
    ั
    0.43
    з
    0.43
    POSITIVE LOGITS
    Dont
    0.63
    Mobil
    0.55
    Log
    0.54
    VY
    0.53
     pedibusque
    0.53
    data
    0.52
    dont
    0.52
    ANS
    0.51
    YS
    0.51
    Invite
    0.50
    Activations Density 0.000%

    No Known Activations