© 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. 163134
    Prev
    Next
    INDEX
    Explanations

    names, stranger

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

    cryptocurrency and financial discussions

    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
     ".$
    0.47
     the
    0.46
     n
    0.45
     >=
    0.44
    াং
    0.44
     obfusc
    0.44
    ob
    0.44
     perceived
    0.43
     επικ
    0.43
     WHERE
    0.43
    POSITIVE LOGITS
    يهه
    0.54
    retta
    0.44
    ्यूम
    0.41
    ച്ച്
    0.41
    اسم
    0.41
    囟
    0.41
    قص
    0.41
    教師
    0.41
     historische
    0.40
     artistique
    0.40
    Activations Density 0.001%

    No Known Activations