© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 163807
    Prev
    Next
    INDEX
    Explanations

    receipts for items

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

    sexualization, traditional culture, July, cumulative, near Polaris, female

    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
    Σ
    0.62
    ই
    0.55
     ש
    0.49
    だが
    0.48
     svak
    0.47
     nhưng
    0.46
    เช่น
    0.46
    כל
    0.46
     loos
    0.45
    ✌
    0.45
    POSITIVE LOGITS
    同时也
    0.46
     designations
    0.42
    abond
    0.40
     publications
    0.40
     bodied
    0.40
     bulletins
    0.39
     तीस
    0.38
     درآمد
    0.38
     Brasile
    0.38
     보겠습니다
    0.38
    Activations Density 0.001%

    No Known Activations