© 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. 60579
    Prev
    Next
    INDEX
    Explanations

    project and vested

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

    instrumental, inexpensive, Alpaca

    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
    訕
    0.46
     Notably
    0.44
     Dazu
    0.43
    }"
    0.42
    ulkar
    0.42
     Karite
    0.42
     Ung
    0.41
     Repeated
    0.40
     unveil
    0.40
     Silk
    0.40
    POSITIVE LOGITS
    ственных
    0.53
    ኡ
    0.52
    ﺭ
    0.52
     repositorio
    0.49
    RENCE
    0.49
    贮
    0.48
     चीन
    0.47
    APTER
    0.47
    ভাসের
    0.46
    REEN
    0.46
    Activations Density 0.000%

    No Known Activations