© 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. 182759
    Prev
    Next
    INDEX
    Explanations

    word followed by another word

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

    object, concept, or domain

    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
    Inspector
    0.55
    Instructor
    0.49
    enstein
    0.48
    Neigh
    0.48
    <b>
    0.48
    neighbours
    0.46
    (("
    0.46
    finally
    0.46
    Dec
    0.45
    Graphics
    0.45
    POSITIVE LOGITS
     assurances
    0.52
     ably
    0.50
     warrantless
    0.47
    믿
    0.47
     metaphors
    0.47
     ferv
    0.46
    జె
    0.46
     speculative
    0.45
     forged
    0.45
    อป
    0.45
    Activations Density 0.000%

    No Known Activations