© 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. 18008
    Prev
    Next
    INDEX
    Explanations

    `Handler` and `Configuration` classes

    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
    았
    0.44
    Native
    0.43
     आधिकारिक
    0.42
    ้ม
    0.42
    '
    0.41
     সো
    0.40
    وال
    0.40
    オス
    0.40
    -[#
    0.40
    ומ
    0.39
    POSITIVE LOGITS
     deceive
    0.42
     offensively
    0.41
    nabi
    0.41
     informé
    0.41
    missing
    0.41
    ס
    0.40
     monologue
    0.40
    ἱ
    0.40
     shoving
    0.40
     convincing
    0.39
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.