© 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. 231491
    Prev
    Next
    INDEX
    Explanations

    academic titles and roles

    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
     Cabin
    0.44
     είναι
    0.44
    垮
    0.42
    Live
    0.41
    升级
    0.40
     eröffnet
    0.40
    λύ
    0.39
     åp
    0.39
    Cabin
    0.39
     القب
    0.39
    POSITIVE LOGITS
    lichkeit
    0.50
    glas
    0.49
     Glas
    0.46
    zneim
    0.46
    ಃ
    0.46
    נו
    0.46
    ableness
    0.46
    ном
    0.46
     maize
    0.45
     docentes
    0.45
    Activations Density 0.001%

    No Known Activations