© 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. 237719
    Prev
    Next
    INDEX
    Explanations

    describing activities or states

    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
    𝓁
    0.53
    渶
    0.52
     horarios
    0.50
    方程
    0.50
    వృద్ధి
    0.49
     சதவீதம்
    0.49
    辈子
    0.49
    aket
    0.47
    洿
    0.47
     ezért
    0.46
    POSITIVE LOGITS
     that
    0.52
     bat
    0.47
    いった
    0.47
     at
    0.47
     this
    0.46
     Pern
    0.45
     lad
    0.45
     my
    0.45
    [])
    0.44
     be
    0.43
    Activations Density 0.001%

    No Known Activations