© 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. 105624
    Prev
    Next
    INDEX
    Explanations

    conversational turns with names

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

    names and titles

    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
     proxim
    0.48
    ，
    0.46
     không
    0.44
     не
    0.44
     pigments
    0.43
     biodegrad
    0.41
     revisions
    0.41
     ""
    0.40
    );}
    0.40
     nomenclature
    0.40
    POSITIVE LOGITS
    我说
    0.48
    मां
    0.44
     Ellos
    0.44
     स्टेडियम
    0.44
     Publikum
    0.44
     அவர்களிடம்
    0.44
    निष्कर्ष
    0.43
    hots
    0.42
     Leute
    0.42
     Leaders
    0.41
    Activations Density 0.019%

    No Known Activations