© 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. 146360
    Prev
    Next
    INDEX
    Explanations

    across cultures

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

    quotes, circular, conditions, chicken, parents

    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
    '
    0.64
     ferrite
    0.55
     categorize
    0.50
     ficou
    0.50
     fabrica
    0.50
     categorized
    0.49
     estimate
    0.49
     sympathize
    0.49
    ఓ
    0.49
     sozinho
    0.48
    POSITIVE LOGITS
     svar
    0.49
     男性
    0.49
    一级
    0.48
    瀆
    0.45
    lje
    0.45
     원
    0.45
    afin
    0.44
    gekehrt
    0.44
    bery
    0.44
    raad
    0.43
    Activations Density 0.001%

    No Known Activations