© 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. 86685
    Prev
    Next
    INDEX
    Explanations

    discusses accomplishments

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

    explaining terms and their actions

    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
    ţin
    0.45
    ・
    0.44
     taraf
    0.43
    ｎ
    0.43
    🇴
    0.43
    adden
    0.42
    ולד
    0.42
    某
    0.42
    অভ
    0.41
    小小
    0.41
    POSITIVE LOGITS
     Ate
    0.43
     సాధ
    0.43
    纮
    0.43
     imbalances
    0.42
     distilled
    0.42
     corticosteroids
    0.42
     Chromatogr
    0.42
     mọi
    0.42
     absor
    0.42
     degrades
    0.41
    Activations Density 0.001%

    No Known Activations