© 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. 121506
    Prev
    Next
    INDEX
    Explanations

    specific mentions

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

    listing or listing items

    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
     tying
    0.55
     fastening
    0.50
    \%).
    0.44
     uttering
    0.44
    .)).
    0.43
    amending
    0.43
     prescribing
    0.41
     fastened
    0.41
    缠
    0.41
     associating
    0.40
    POSITIVE LOGITS
    画布
    0.48
     minha
    0.46
     Chopin
    0.45
     maya
    0.45
    pyplot
    0.44
    μα
    0.44
    masa
    0.44
     בש
    0.43
    Fhir
    0.43
    רית
    0.43
    Activations Density 0.000%

    No Known Activations