© 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. 87564
    Prev
    Next
    INDEX
    Explanations

    finding algorithms or terminology

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

    specific words followed by actions

    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
    년간
    0.45
     ^
    0.45
     عين
    0.45
    攺
    0.44
     (
    0.43
    istant
    0.42
     जान
    0.41
    Named
    0.41
    weite
    0.41
    eil
    0.41
    POSITIVE LOGITS
    Cober
    0.44
    がか
    0.43
     znamen
    0.42
     dSample
    0.41
     파인더
    0.41
    ρό
    0.41
    ップ
    0.41
     idempot
    0.40
    雫
    0.40
    Fantasy
    0.40
    Activations Density 0.000%

    No Known Activations