© 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. 49200
    Prev
    Next
    INDEX
    Explanations

    start of phrases

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

    subjective

    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
     then
    0.47
     T
    0.43
    他们
    0.42
     R
    0.41
     Ton
    0.41
     විශ
    0.41
     رأس
    0.40
     Guildford
    0.40
     Dow
    0.40
    လည်း
    0.40
    POSITIVE LOGITS
    katore
    0.49
    laug
    0.48
    argento
    0.46
    cuando
    0.46
     молоко
    0.45
    اعة
    0.43
    ἢ
    0.43
    묽
    0.42
    pending
    0.42
    gramModel
    0.42
    Activations Density 0.000%

    No Known Activations