© 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. 34767
    Prev
    Next
    INDEX
    Explanations

    services and packages

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

    lanes, supporter, prolonged use

    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
    t
    0.58
    ت
    0.55
    BLO
    0.52
    տ
    0.52
    sz
    0.51
     BLOOD
    0.50
    asati
    0.50
    س
    0.50
    ศี
    0.48
    ר
    0.48
    POSITIVE LOGITS
     cosm
    0.46
     melting
    0.41
    MyToolkit
    0.41
     গুল
    0.40
     freezing
    0.40
    ისუფ
    0.39
     程
    0.38
    François
    0.38
     homology
    0.37
    百
    0.37
    Activations Density 0.000%

    No Known Activations