© 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. 42102
    Prev
    Next
    INDEX
    Explanations

    PMO services

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

    suggestions for adding or changing phrases

    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
    ort
    0.47
    arlı
    0.43
     European
    0.43
     EURO
    0.43
    𝙴
    0.41
     virtually
    0.40
     Io
    0.40
    EURO
    0.40
     Euro
    0.40
     Wildlife
    0.39
    POSITIVE LOGITS
     lysates
    0.52
     Pública
    0.49
     دیے
    0.48
     धारणा
    0.47
    氿
    0.47
    भाषित
    0.46
    ☭
    0.46
    Semitism
    0.46
    RatingDiff
    0.44
    कांग्रेस
    0.44
    Activations Density 0.000%

    No Known Activations