© 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. 133736
    Prev
    Next
    INDEX
    Explanations

    foreign language characters

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

    scenario explanation

    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
    e
    0.46
    eig
    0.46
    });
    0.44
     Russell
    0.44
    %,
    0.41
     Epstein
    0.41
    %;
    0.41
    "));
    0.40
    qw
    0.40
    zone
    0.39
    POSITIVE LOGITS
    🚐
    0.53
    కి
    0.53
    缡
    0.53
    뤽
    0.53
    ങ്ക്
    0.52
     뭐라고
    0.52
    ە
    0.52
    辂
    0.52
     étapes
    0.51
    스키
    0.51
    Activations Density 0.002%

    No Known Activations