© 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-16K
    7. 12933
    Prev
    Next
    INDEX
    Explanations

    Sunninghill

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

    marriage and sex

    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_16k_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
     डाउनलोड
    0.46
     алыңыз
    0.45
     казіно
    0.45
     그거
    0.41
     қ
    0.41
    мець
    0.41
     جبت
    0.41
    粿
    0.40
     нажмите
    0.40
    ICHIGAN
    0.40
    POSITIVE LOGITS
    če
    0.43
    param
    0.41
    sa
    0.40
     [[[
    0.39
    all
    0.39
    ever
    0.39
    utada
    0.39
    slab
    0.39
    cau
    0.38
    adr
    0.38
    Activations Density 0.061%

    No Known Activations