© 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. 16714
    Prev
    Next
    INDEX
    Explanations

    regarding or concerning entities

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

    entity toward or regarding

    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
     Fewer
    0.46
    ający
    0.43
     thinks
    0.43
    aço
    0.42
     fewer
    0.41
    u
    0.40
    uv
    0.40
     দিয়ে
    0.39
    </em>
    0.39
     advised
    0.39
    POSITIVE LOGITS
     تجاه
    0.59
     privind
    0.55
     щодо
    0.51
     dotyczące
    0.46
     terhadap
    0.46
     بشأن
    0.45
     заключается
    0.44
    に関する
    0.43
     dotycz
    0.43
     حکمت
    0.42
    Activations Density 0.117%

    No Known Activations