© 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. 234210
    Prev
    Next
    INDEX
    Explanations

    groups or following specific words

    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
    ;
    0.47
     apocalypse
    0.47
     whites
    0.46
     contests
    0.46
     awful
    0.46
     manufacturers
    0.46
     butchers
    0.45
     advocates
    0.44
     commencement
    0.44
     advocacy
    0.43
    POSITIVE LOGITS
     ਦਿੱ
    0.51
    abilités
    0.47
    ይ
    0.47
     ठर
    0.46
    PASS
    0.46
    Backup
    0.45
     Hochsch
    0.45
     個人
    0.45
    腧
    0.44
     स्थानिक
    0.44
    Activations Density 0.001%

    No Known Activations