© 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. 21307
    Prev
    Next
    INDEX
    Explanations

    relative file paths

    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
     பதில
    0.43
     ല
    0.42
     পুরোপুরি
    0.42
    ಾ
    0.42
    ್ಟ
    0.41
     이용
    0.40
     файла
    0.40
    ு
    0.40
     Completely
    0.40
     ২০২১
    0.39
    POSITIVE LOGITS
    fellow
    0.44
    ance
    0.42
    onne
    0.42
    hem
    0.42
    grained
    0.41
    flies
    0.41
    ies
    0.40
    .“
    0.40
    grain
    0.40
    delegate
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.