© 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. 7131
    Prev
    Next
    INDEX
    Explanations

    'm 's

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

    foreign language thanks

    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
     Hayward
    0.25
    Bx
    0.23
    Strawberry
    0.23
    3
    0.23
     Strawberry
    0.23
    াদশ
    0.22
     отлично
    0.22
     Saratoga
    0.22
     Appalachian
    0.22
    1
    0.22
    POSITIVE LOGITS
     CONCLUS
    0.28
     humiliation
    0.26
    最後に
    0.25
    <eos>
    0.25
    END
    0.25
     víct
    0.24
    Коммента
    0.24
     infine
    0.24
     concl
    0.24
     humiliated
    0.23
    Activations Density 0.396%

    No Known Activations