© 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. 238610
    Prev
    Next
    INDEX
    Explanations

    medium package, black gold

    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
    Roxy
    0.54
    Calle
    0.51
    0
    0.49
    6
    0.49
    Go
    0.49
    Guys
    0.48
    Gu
    0.47
     Frau
    0.47
    Lady
    0.46
    Bru
    0.46
    POSITIVE LOGITS
    ӡ
    0.47
     stimul
    0.46
    u
    0.46
     oblique
    0.45
    動畫
    0.45
    ப்படி
    0.45
    潛行
    0.45
     cốt
    0.45
     mū
    0.44
    ヂ
    0.44
    Activations Density 0.001%

    No Known Activations