© 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. 7915
    Prev
    Next
    INDEX
    Explanations

    business abbreviations and roles

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

    acronyms and abbreviations

    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
    ucapkan
    0.47
     Ι
    0.46
    괵
    0.46
    FBSDKInternal
    0.45
    MODKEY
    0.45
    ﺴ
    0.45
    ]=\
    0.45
    ྥ
    0.45
    पहर
    0.44
     তবে
    0.44
    POSITIVE LOGITS
    و
    1.09
    на
    1.02
    ו
    0.92
    2
    0.87
     on
    0.84
    ف
    0.80
    1
    0.78
    the
    0.73
    ح
    0.73
    ка
    0.72
    Activations Density 0.796%

    No Known Activations