© 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. 86543
    Prev
    Next
    INDEX
    Explanations

    financial planners

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

    sorting alphabetically

    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
     घोषित
    0.47
     တစ်
    0.45
     트
    0.44
     건설
    0.43
    したがって
    0.42
    erie
    0.42
    에
    0.41
    n
    0.41
    proficiency
    0.41
     ਸੁ
    0.41
    POSITIVE LOGITS
    MRI
    0.45
    Potion
    0.44
     redshifts
    0.44
    ροσ
    0.44
    Packard
    0.43
    个体
    0.43
    MHz
    0.42
    Roxy
    0.42
    Mary
    0.42
    Raster
    0.42
    Activations Density 0.000%

    No Known Activations