© 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. 128669
    Prev
    Next
    INDEX
    Explanations

    permissions, free services, or conditions

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

    classification of things

    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
    Dedicated
    0.48
    HYDRO
    0.47
    ⸝
    0.45
     신고
    0.42
    La
    0.42
    hydro
    0.41
     thermodynamics
    0.41
    CY
    0.41
    Blocks
    0.40
    Jak
    0.40
    POSITIVE LOGITS
    iód
    0.54
    igil
    0.52
    []>
    0.50
    యన్
    0.48
     ग्रेटर
    0.48
    nan
    0.47
    సర్
    0.46
     campeón
    0.45
    соеди
    0.45
    uleiro
    0.45
    Activations Density 0.000%

    No Known Activations