© 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. 126230
    Prev
    Next
    INDEX
    Explanations

    without previous

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

    However, although, throughout

    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
    ទេ។
    0.49
    ところが
    0.48
     ненави
    0.46
    }).
    0.45
     horrors
    0.45
    量は
    0.45
    跑到
    0.44
    をご覧
    0.43
     lire
    0.43
     annoy
    0.42
    POSITIVE LOGITS
     برد
    0.48
    ulph
    0.44
    -¹
    0.44
    缆
    0.43
    jų
    0.43
     geldig
    0.43
    Administrator
    0.42
     নন্দ
    0.42
     CFRP
    0.42
    acyjnych
    0.41
    Activations Density 0.000%

    No Known Activations