© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 224429
    Prev
    Next
    INDEX
    Explanations

    names and entities

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

    numbers and scales

    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
    .'
    0.51
    >'
    0.47
     piper
    0.46
     absolutamente
    0.45
     golf
    0.45
    Bailey
    0.45
    Como
    0.45
     Lake
    0.44
    Rey
    0.44
     LIKE
    0.44
    POSITIVE LOGITS
    ಗಳಿಂದ
    0.46
     mengenal
    0.43
    閑
    0.43
    গুরু
    0.42
    勧め
    0.41
    comodule
    0.41
    聝
    0.41
    建て
    0.41
    叢
    0.40
     চাল
    0.40
    Activations Density 0.001%

    No Known Activations