© 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. 33709
    Prev
    Next
    INDEX
    Explanations

    colourful things

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

    concatenating or aspects

    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
     teljesen
    0.45
     शासन
    0.42
    完全に
    0.41
     완전히
    0.41
     zewnętrzne
    0.40
     totalement
    0.40
    뇽
    0.39
     helemaal
    0.39
     voisin
    0.39
    bergement
    0.38
    POSITIVE LOGITS
    та
    0.46
     кухня
    0.45
    তা
    0.44
     afferma
    0.44
    İK
    0.43
    馄
    0.42
    println
    0.42
     তারাই
    0.41
    ين
    0.41
     alice
    0.41
    Activations Density 0.000%

    No Known Activations