© 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. 251069
    Prev
    Next
    INDEX
    Explanations

    specific nouns and concepts

    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
     पदा
    0.47
     lecz
    0.46
    en
    0.46
    of
    0.45
    av
    0.45
    Ნ
    0.45
    து
    0.44
    ྱ
    0.44
     основы
    0.43
     तथा
    0.43
    POSITIVE LOGITS
    britannien
    0.50
    كون
    0.47
    ingles
    0.44
     Hins
    0.44
    ليم
    0.44
    جاه
    0.43
    ليك
    0.43
    蓓
    0.42
    都會
    0.41
     نوم
    0.41
    Activations Density 0.001%

    No Known Activations