© 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. 46108
    Prev
    Next
    INDEX
    Explanations

    sharing is caring

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

    don't feel like

    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
    E
    0.58
    3
    0.49
    ND
    0.47
    X
    0.46
    stan
    0.46
    R
    0.46
    U
    0.46
    B
    0.46
    -
    0.45
     qualification
    0.45
    POSITIVE LOGITS
     Audiodateien
    0.46
     joten
    0.44
     adware
    0.43
     golfers
    0.43
     perpetrated
    0.43
     ใคร
    0.42
     พี่
    0.42
     retailers
    0.41
     incarcerated
    0.41
     saute
    0.41
    Activations Density 0.000%

    No Known Activations