© 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. 152322
    Prev
    Next
    INDEX
    Explanations

    judge, Nam, Place

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

    delivered in

    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
     devono
    0.54
     повинні
    0.54
    цію
    0.50
     ज्योग्राफी
    0.50
     possono
    0.50
    assati
    0.49
    и
    0.49
    ким
    0.49
     можуть
    0.48
    𝓾
    0.48
    POSITIVE LOGITS
     NAM
    0.45
    Nam
    0.42
     bakteri
    0.42
    Bir
    0.42
    جان
    0.41
    </td>
    0.41
     Place
    0.41
     birch
    0.41
     এপ্রিল
    0.41
    <unused2172>
    0.40
    Activations Density 0.000%

    No Known Activations