© 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. 202068
    Prev
    Next
    INDEX
    Explanations

    fry, putting, enclosure, each, only, supporting

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

    "ready to"

    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
     IndexError
    0.45
    اضره
    0.45
    윳
    0.45
     町
    0.43
     vacanam
    0.43
    是對
    0.42
     Jacks
    0.42
    のは
    0.41
     க்கு
    0.41
     اولین
    0.41
    POSITIVE LOGITS
    ר
    0.53
    partnership
    0.53
    ou
    0.48
    ون
    0.48
    р
    0.47
    perme
    0.46
    artist
    0.46
    лле
    0.46
     eind
    0.46
    enuine
    0.46
    Activations Density 0.000%

    No Known Activations