© 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. 54751
    Prev
    Next
    INDEX
    Explanations

    strong C

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

    pre-ejaculate fluid release

    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
    ’
    0.52
     Chairman
    0.48
     Hopkins
    0.48
     FAST
    0.47
     conscientes
    0.47
    Y
    0.47
    Gl
    0.46
     OSHA
    0.45
    S
    0.45
    O
    0.45
    POSITIVE LOGITS
     subdir
    0.52
    גם
    0.47
     גם
    0.47
    があるので
    0.47
     придется
    0.47
     myös
    0.43
     확대
    0.43
    しも
    0.43
     ankaŭ
    0.43
     submodule
    0.43
    Activations Density 0.000%

    No Known Activations