© 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. 203120
    Prev
    Next
    INDEX
    Explanations

    Carbon derived

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

    liquid soap or digital marketing

    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
    i
    0.60
     directories
    0.55
     riffs
    0.55
     experiments
    0.54
     optimality
    0.54
     assays
    0.53
     agencies
    0.52
     electrophoresis
    0.52
     correlates
    0.51
     theories
    0.51
    POSITIVE LOGITS
    ☦
    0.47
    ूज
    0.46
    Infinite
    0.46
    旻
    0.45
    ovjek
    0.43
    ólito
    0.43
    無い
    0.43
    訫
    0.43
    芠
    0.43
    াং
    0.43
    Activations Density 0.001%

    No Known Activations