© 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. 189813
    Prev
    Next
    INDEX
    Explanations

    academic citations and related words

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

    interesting factsorcommitmentsorlisteningorhitchorcourage

    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
     EDM
    0.52
     Airlines
    0.47
    ivity
    0.46
    Works
    0.45
    ।’
    0.45
    ।’’
    0.44
    Juan
    0.44
    ഽ
    0.43
    なわち
    0.43
    rying
    0.43
    POSITIVE LOGITS
    том
    0.55
    стям
    0.47
    طنين
    0.47
     nascent
    0.46
    볕
    0.46
     estern
    0.46
    τρ
    0.45
    ל
    0.45
    𝗁
    0.45
    tn
    0.45
    Activations Density 0.000%

    No Known Activations