© 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. 188594
    Prev
    Next
    INDEX
    Explanations

    proper nouns and specific terms

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

    striving for API access

    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
    茧
    0.47
     дал
    0.46
     данного
    0.45
    晞
    0.44
     ჩ
    0.44
    paired
    0.44
     ಮತ್ತ
    0.43
    나
    0.43
    चलित
    0.43
     Singing
    0.43
    POSITIVE LOGITS
    ol
    0.49
     trao
    0.48
    urada
    0.46
     conta
    0.45
     ngon
    0.43
     dvě
    0.43
     dent
    0.43
     pdf
    0.42
     olduğu
    0.42
    গ্রাফ
    0.42
    Activations Density 0.001%

    No Known Activations