© 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. 184505
    Prev
    Next
    INDEX
    Explanations

    website URLs and online activity

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

    descriptions of things

    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
     Վ
    0.54
     Fits
    0.50
    }.
    0.49
    绑定
    0.47
    中
    0.47
    0.46
    ).
    0.44
    内存
    0.44
    ดังกล่าว
    0.44
     Inher
    0.44
    POSITIVE LOGITS
     diathermy
    0.49
     verbal
    0.47
     brace
    0.45
     disinformation
    0.45
    council
    0.45
     subpoena
    0.44
     bolo
    0.44
     balón
    0.44
     vaksin
    0.43
    nominal
    0.43
    Activations Density 0.001%

    No Known Activations