© 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. 12378
    Prev
    Next
    INDEX
    Explanations

    end of phrases with punctuation

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

    sequences of digits and hyphens

    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
    m
    0.47
     предоставля
    0.44
     OUTPUT
    0.44
    dzie
    0.42
     custodians
    0.41
    nominated
    0.41
     nominated
    0.41
     dependents
    0.41
     infring
    0.41
    dostęp
    0.40
    POSITIVE LOGITS
     to
    0.50
     is
    0.50
    ية
    0.48
    л
    0.48
     of
    0.48
    ushka
    0.47
    .#
    0.45
    ة
    0.44
     Champlain
    0.43
    .​​
    0.43
    Activations Density 0.000%

    No Known Activations