© 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. 145842
    Prev
    Next
    INDEX
    Explanations

    the unit

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

    generate consistent profit

    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
     üç
    0.61
     éclat
    0.57
    ése
    0.56
    𝚣
    0.54
     écl
    0.53
     তিন
    0.53
     incredibly
    0.52
    éric
    0.52
     bł
    0.52
    odont
    0.51
    POSITIVE LOGITS
    FACTORY
    0.45
    Where
    0.43
    <td>
    0.43
    Mob
    0.42
    V
    0.42
    AVE
    0.40
    實
    0.40
    ALES
    0.39
    Certainly
    0.39
    State
    0.39
    Activations Density 0.002%

    No Known Activations