© 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. 14088
    Prev
    Next
    INDEX
    Explanations

    located in

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

    explaining future results

    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
    FindFileData
    0.47
    valentine
    0.46
     Вален
    0.45
    박
    0.44
     कोरिया
    0.44
    匡
    0.44
    ：《
    0.43
    ल्लाला
    0.43
    Valentine
    0.42
    변경된
    0.42
    POSITIVE LOGITS
     Sam
    0.49
     Saty
    0.47
     Guys
    0.45
     Similarly
    0.45
     =
    0.44
     deviations
    0.43
     Bad
    0.43
     Universidad
    0.43
     Algebra
    0.42
     But
    0.42
    Activations Density 0.000%

    No Known Activations