© 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. 42405
    Prev
    Next
    INDEX
    Explanations

    you like, the survey

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

    actions, purposes, states

    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
    ﻌ
    0.55
    껐
    0.53
    욘
    0.51
    ясь
    0.48
    detalle
    0.47
    ajući
    0.46
    러스
    0.46
    trades
    0.46
     korišten
    0.46
    ляць
    0.45
    POSITIVE LOGITS
     Ninth
    0.45
     Basilica
    0.45
     \&
    0.45
     استح
    0.44
     Monroe
    0.44
     Bueno
    0.43
     och
    0.43
     Fernandes
    0.43
     Clarendon
    0.43
     After
    0.43
    Activations Density 0.000%

    No Known Activations