© 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. 203655
    Prev
    Next
    INDEX
    Explanations

    by particular assist require

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

    Stack structure, project setup, world possibilities, how to, domain configuration

    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
    ﻬ
    0.52
    ﻻ
    0.51
    HCO
    0.46
    わからない
    0.46
    ﺎ
    0.46
    Injection
    0.46
    ;"+
    0.46
    रे
    0.45
    INDU
    0.45
    ﻫ
    0.45
    POSITIVE LOGITS
     Betriebs
    0.54
     Pent
    0.53
     Magistrates
    0.51
     Naked
    0.51
     Prolog
    0.48
     Audrey
    0.48
     Betrieb
    0.48
     Mak
    0.47
     Trouver
    0.47
     Maest
    0.47
    Activations Density 0.000%

    No Known Activations