© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 75734
    Prev
    Next
    INDEX
    Explanations

    presenting features

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

    feature or features

    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
    Negative Logits
     of
    0.94
    AY
    0.89
    3
    0.84
     as
    0.80
    Y
    0.80
     on
    0.79
    CHREIB
    0.79
    ่
    0.77
    ی
    0.74
     கருதப்படுகிறது
    0.74
    POSITIVE LOGITS
     prominently
    1.22
    ob
    0.94
    on
    0.92
    st
    0.92
    och
    0.92
    },
    0.91
     vocals
    0.86
    。
    0.83
    áme
    0.82
    0.82
    Activations Density 0.085%

    No Known Activations