© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 884
    Prev
    Next
    INDEX
    Explanations

    instruction prompts and code 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_53_width_65k_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
     upside
    0.70
    ⇅
    0.48
     Inverse
    0.47
     inverted
    0.47
     hh
    0.44
    inverted
    0.43
    HH
    0.43
    Inverse
    0.43
     HH
    0.42
    BOTTOM
    0.42
    POSITIVE LOGITS
     (/
    0.42
    izos
    0.40
     modalités
    0.40
    uis
    0.39
     fen
    0.38
     ../
    0.38
    íos
    0.38
     строи
    0.38
    fen
    0.37
     ~/
    0.37
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.