© 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. 245369
    Prev
    Next
    INDEX
    Explanations

    Google searches

    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
    :
    0.57
    <<
    0.46
    ът
    0.45
     Дан
    0.45
    :...
    0.45
    னையும்
    0.45
    вно
    0.44
    ުން
    0.44
    Vox
    0.44
     баскетбол
    0.44
    POSITIVE LOGITS
     unsaturated
    0.46
    强大
    0.45
     alkyl
    0.44
     moustache
    0.44
    電影
    0.43
     upang
    0.43
     mengatur
    0.43
    猗
    0.43
    mipmap
    0.43
     Alibaba
    0.42
    Activations Density 0.001%

    No Known Activations