© 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. 56933
    Prev
    Next
    INDEX
    Explanations

    performing arts and dreams

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

    exploring definitions and complexity

    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
    不
    0.47
    튠
    0.45
    質
    0.44
    了一
    0.43
    ิจ
    0.42
    明
    0.42
    不上
    0.42
    評価
    0.41
    ÁN
    0.41
    憤
    0.41
    POSITIVE LOGITS
     manifestaciones
    0.51
     बुला
    0.50
     segítség
    0.48
    Diameter
    0.47
     messageFields
    0.45
     actividades
    0.45
    Sprite
    0.45
     поскольку
    0.44
     enormes
    0.44
    Frankreich
    0.43
    Activations Density 0.000%

    No Known Activations