© 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. 121987
    Prev
    Next
    INDEX
    Explanations

    exclusively for

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

    thoughts on analysis

    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
     গ্যাস
    0.56
     neutrons
    0.54
     නිෂ්
    0.54
     श्रमिक
    0.54
     washers
    0.54
     राजमार्ग
    0.54
    Ⴖ
    0.53
     मजदूर
    0.53
    ्याज
    0.52
     matrice
    0.52
    POSITIVE LOGITS
     Account
    0.51
    !)
    0.48
    ')
    0.47
    ’)
    0.47
     it
    0.47
    ');
    0.44
    CAPE
    0.44
    する場合は
    0.44
    ه
    0.43
    gerald
    0.42
    Activations Density 0.000%

    No Known Activations