© 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. 12119
    Prev
    Next
    INDEX
    Explanations

    award winning

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

    showcasing feline, actions are

    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
    ,​
    0.42
     المالية
    0.42
     €,
    0.41
     Kart
    0.41
     Wake
    0.41
     Fehl
    0.41
     okazji
    0.40
     Iso
    0.40
     informática
    0.40
     Pulp
    0.40
    POSITIVE LOGITS
    fds
    0.51
    YH
    0.47
    Joining
    0.46
    細
    0.46
    最终
    0.46
    ename
    0.45
    وسیع
    0.44
    ществует
    0.44
    箒
    0.44
    DESTROY
    0.44
    Activations Density 0.000%

    No Known Activations