© 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. 137243
    Prev
    Next
    INDEX
    Explanations

    expectations, writer, names

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

    purchase history/email verification

    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
    Ἔ
    0.52
    revista
    0.47
     lancio
    0.47
    στο
    0.46
    রণে
    0.45
    र्द
    0.45
    문에
    0.45
    வைத்த
    0.45
    mathbb
    0.43
    enciones
    0.43
    POSITIVE LOGITS
     因为
    0.49
    buildSpec
    0.45
    URIComponent
    0.44
     $<
    0.43
     sınır
    0.43
    ابس
    0.42
    િયન
    0.41
    同学
    0.41
     \|
    0.39
     $<\
    0.39
    Activations Density 0.003%

    No Known Activations