© 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. 232130
    Prev
    Next
    INDEX
    Explanations

    official statements and details

    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
     ersetzt
    0.50
    তান্ত্রিক
    0.48
     spoloč
    0.48
    㜖
    0.46
    GroupBox
    0.44
     ибо
    0.44
    వంటి
    0.44
     DecodingError
    0.43
    的使用
    0.43
     übertr
    0.42
    POSITIVE LOGITS
    গ
    0.48
    Lieutenant
    0.47
    Nashville
    0.47
    صی
    0.45
     दिन
    0.44
    ົບ
    0.43
    It
    0.43
     ganglion
    0.43
    mole
    0.43
    tements
    0.42
    Activations Density 0.001%

    No Known Activations