© 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. 210684
    Prev
    Next
    INDEX
    Explanations

    accessing the service

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

    disruptive, classic, precision, aims

    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
    িখ
    0.50
     Presentations
    0.48
    iken
    0.48
     Дан
    0.46
     CPD
    0.45
     conferred
    0.45
     présente
    0.45
    扂
    0.45
    trk
    0.44
    ৬৮
    0.44
    POSITIVE LOGITS
    वि
    0.57
    අ
    0.57
    У
    0.56
    उ
    0.54
    உ
    0.52
    أ
    0.50
    0.50
    DIG
    0.49
    Т
    0.48
    u
    0.48
    Activations Density 0.000%

    No Known Activations