© 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. 1231
    Prev
    Next
    INDEX
    Explanations

    names of airlines

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

    prediction and warning

    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
     I
    0.29
     you
    0.29
     M
    0.29
     B
    0.28
     S
    0.28
     G
    0.27
     we
    0.26
     P
    0.25
     youll
    0.25
     spots
    0.24
    POSITIVE LOGITS
    OpportunitiesBy
    0.30
     unlaw
    0.28
    誣
    0.26
     unlawfully
    0.26
    లేదు
    0.25
     økonom
    0.25
    害怕
    0.25
     незакон
    0.24
    诬
    0.24
    GEBURTS
    0.24
    Activations Density 0.000%

    No Known Activations