© 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. 54638
    Prev
    Next
    INDEX
    Explanations

    when or Hershey

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

    explaining specific goals and products

    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
    ToBase
    0.55
    Vaterpolo
    0.46
     dragState
    0.46
    证
    0.45
    newState
    0.43
    联
    0.43
    ٹا
    0.42
    Substitute
    0.42
    Mason
    0.42
    UserState
    0.42
    POSITIVE LOGITS
     pero
    0.51
     aber
    0.49
     misdeme
    0.47
     (
    0.46
     lähe
    0.46
     Hass
    0.46
     maar
    0.46
     producto
    0.45
     billing
    0.45
     about
    0.44
    Activations Density 0.000%

    No Known Activations