© 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. 160354
    Prev
    Next
    INDEX
    Explanations

    angles, sequence, generation

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

    explaining names and descriptions

    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
     तर्क
    0.50
    :")
    0.48
     Approval
    0.46
     prestar
    0.45
     Approved
    0.44
     страницы
    0.44
     verwacht
    0.44
    inin
    0.43
     दिसम्बर
    0.43
     والش
    0.43
    POSITIVE LOGITS
    SEQUENCE
    0.50
    ྱ
    0.47
     morphological
    0.46
     sequence
    0.46
     lineages
    0.45
     casein
    0.45
     constitut
    0.44
     filamentous
    0.44
     recombinant
    0.44
    rization
    0.44
    Activations Density 0.001%

    No Known Activations