© 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. 143172
    Prev
    Next
    INDEX
    Explanations

    forehead lines

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

    males are larger than females

    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
    有很多
    0.50
     nutrientes
    0.44
    φαν
    0.43
    亟
    0.43
    坦
    0.41
    च
    0.41
     reforms
    0.41
    防控
    0.41
    চরা
    0.41
     agendas
    0.40
    POSITIVE LOGITS
     Ż
    0.53
     ቲ
    0.49
     Gu
    0.48
     ሽፋን
    0.48
     tyr
    0.47
    ErrorCode
    0.46
     tys
    0.46
     Gj
    0.45
     Jun
    0.45
     Si
    0.44
    Activations Density 0.000%

    No Known Activations