© 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. 29590
    Prev
    Next
    INDEX
    Explanations

    should be, largest coffee, is the

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

    can perform tasks

    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
    াচিত
    0.48
     کیسے
    0.43
     ước
    0.41
    abbanti
    0.40
     shrinkage
    0.40
     recurs
    0.40
     감소
    0.40
    ֛
    0.40
     liable
    0.39
    ক্ষিতে
    0.39
    POSITIVE LOGITS
     Mondo
    0.46
     algorith
    0.43
    ﻒ
    0.43
     aparelho
    0.43
    ramar
    0.43
    StatusCodes
    0.42
    Br
    0.42
     FIXME
    0.42
     Jeder
    0.42
    掌握
    0.42
    Activations Density 0.000%

    No Known Activations