© 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. 124791
    Prev
    Next
    INDEX
    Explanations

    service our, if it, glue it, facility we

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

    naive approach

    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
    परी
    0.45
    洗濯
    0.43
     дале
    0.43
    хий
    0.42
     beard
    0.42
    蝉
    0.42
    ولو
    0.42
     entsch
    0.42
    нский
    0.42
    ارب
    0.41
    POSITIVE LOGITS
    tyw
    0.52
    ţ
    0.44
     surrounded
    0.43
     pojawi
    0.42
     spong
    0.42
    ț
    0.42
     kan
    0.41
     located
    0.41
     bounded
    0.41
     flanked
    0.41
    Activations Density 0.000%

    No Known Activations