© 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. 34278
    Prev
    Next
    INDEX
    Explanations

    the + noun/adjective

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

    STAR method or option

    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
     reak
    0.44
    来源于
    0.43
     bouts
    0.41
     deriving
    0.40
     detonations
    0.39
    ̈́
    0.39
     atyp
    0.39
    ̣
    0.39
     pochod
    0.38
    WART
    0.38
    POSITIVE LOGITS
     guidelines
    0.51
     Функция
    0.49
     አማ
    0.47
     easiest
    0.46
     helpline
    0.46
     हेल्पलाइन
    0.44
     допомогою
    0.44
     guideline
    0.44
     option
    0.44
     Google
    0.44
    Activations Density 0.077%

    No Known Activations