© 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. 159998
    Prev
    Next
    INDEX
    Explanations

    in the

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

    defining purpose

    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
    バイト
    0.50
     hormati
    0.48
    γγελμα
    0.47
    忔
    0.47
    пень
    0.46
    うえ
    0.46
     motionProxy
    0.46
    ク
    0.46
    ሆነ
    0.46
     mnist
    0.46
    POSITIVE LOGITS
    un
    0.62
    le
    0.54
    um
    0.53
    inking
    0.50
    as
    0.49
    us
    0.49
    rain
    0.47
    at
    0.47
    ungal
    0.47
    res
    0.46
    Activations Density 0.000%

    No Known Activations