© 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. 15439
    Prev
    Next
    INDEX
    Explanations

    spiekothek

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

    legal and policy information

    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
    <i>
    0.61
    <b>
    0.58
    section
    0.55
    <strong>
    0.53
    on
    0.52
    на
    0.51
    【
    0.50
    <em>
    0.47
    case
    0.46
     in
    0.46
    POSITIVE LOGITS
     caoutch
    0.57
     azonban
    0.54
     apparence
    0.52
     vattum
    0.50
     aantal
    0.50
     RasterModelGrid
    0.49
     antal
    0.49
     carénés
    0.48
     नकार
    0.48
     logements
    0.48
    Activations Density 0.000%

    No Known Activations