© 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. 13718
    Prev
    Next
    INDEX
    Explanations

    place names and proper nouns

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

    limitations and AI value

    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
    ージャ
    0.47
    او
    0.43
    บบ
    0.42
    ולוג
    0.41
     fullest
    0.40
    Бы
    0.40
    😚
    0.40
    寤
    0.40
    பு
    0.40
    Animals
    0.40
    POSITIVE LOGITS
    ost
    0.44
    akia
    0.43
     および
    0.43
    era
    0.43
    ances
    0.43
    lin
    0.43
    ers
    0.42
     மதி
    0.42
    lan
    0.42
    ancio
    0.41
    Activations Density 0.001%

    No Known Activations