© 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. 57806
    Prev
    Next
    INDEX
    Explanations

    numbers, editions, and years

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

    describing change and movement

    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
    ﺲ
    0.60
    рино
    0.54
    لی
    0.53
    лах
    0.52
    ках
    0.51
    бле
    0.49
    𝜁
    0.48
    änen
    0.48
    株式会社
    0.48
    нал
    0.47
    POSITIVE LOGITS
    </code>
    0.52
     revealed
    0.47
     emot
    0.47
     ot
    0.44
     described
    0.43
     closeModal
    0.43
     descrito
    0.43
     disclosed
    0.42
     Attributes
    0.42
     commentator
    0.42
    Activations Density 0.001%

    No Known Activations