© 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. 173136
    Prev
    Next
    INDEX
    Explanations

    listings online, candidate, prospect, such as

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

    potential, Unlock, the, actually, columns, according

    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
    ا
    0.59
    的设计
    0.53
    lső
    0.52
    位于
    0.50
    vět
    0.49
    ဟု
    0.49
    胍
    0.49
    و
    0.48
    oled
    0.48
    žu
    0.48
    POSITIVE LOGITS
     b
    0.52
    АР
    0.47
     palsy
    0.46
     mero
    0.46
     barbers
    0.46
     пого
    0.45
     Yed
    0.45
     llave
    0.45
     relleno
    0.45
     goddess
    0.44
    Activations Density 0.000%

    No Known Activations