© 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. 157412
    Prev
    Next
    INDEX
    Explanations

    `half after`

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

    geographic locations and specific terms

    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
    ність
    0.42
     oxalic
    0.42
     réfrig
    0.42
     acids
    0.40
     Viruses
    0.40
    🤍
    0.40
     carcinogenic
    0.39
     viruses
    0.39
     Trivia
    0.38
     έγ
    0.38
    POSITIVE LOGITS
    RESOURCE
    0.49
     matem
    0.49
     मैथमेट
    0.48
    Mathematical
    0.47
    towards
    0.47
     भुव
    0.46
    Shake
    0.46
    Œ
    0.46
     talleres
    0.46
    飛ば
    0.46
    Activations Density 0.000%

    No Known Activations