© 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. 24940
    Prev
    Next
    INDEX
    Explanations

    System. followed by namespace

    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
     fermions
    0.41
     asserting
    0.37
    <unused63>
    0.36
     resorption
    0.36
     And
    0.36
    િંહ
    0.35
     accessing
    0.35
     accesses
    0.34
    And
    0.33
     lands
    0.32
    POSITIVE LOGITS
    ológicos
    0.46
     novembro
    0.45
     ಎಷ್ಟು
    0.44
     привести
    0.43
     टाक्या
    0.43
    ༣
    0.42
    kiye
    0.42
    <unused22>
    0.42
    皈
    0.42
     doda
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.