© 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. 80966
    Prev
    Next
    INDEX
    Explanations

    conditions or limitations

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

    sampling with replacement

    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
     करना
    0.44
    ޏ
    0.42
     जिम्मेदारी
    0.41
     केंद्रा
    0.41
     нужны
    0.41
     دینا
    0.40
    <unused29>
    0.39
     রাখতে
    0.39
     finalmente
    0.38
     একা
    0.38
    POSITIVE LOGITS
    entr
    0.46
     epist
    0.44
    無論
    0.44
    zeit
    0.43
    science
    0.42
    featuring
    0.42
    ਸ
    0.41
    this
    0.41
     Farr
    0.40
    artis
    0.40
    Activations Density 0.000%

    No Known Activations