© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 101885
    Prev
    Next
    INDEX
    Explanations

    reporting claims or uncertainties

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

    This neuron flags content words in headlines and titles (e.g. sports headlines, announcements, or question titles).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     itself
    -1.35
     as
    -1.19
     with
    -1.13
     when
    -1.10
     and
    -1.06
     more
    -1.05
    чник
    -1.02
     и
    -1.02
     which
    -1.01
     original
    -1.01
    POSITIVE LOGITS
     возможно
    1.30
    feliz
    1.16
     mungkin
    1.12
     semuanya
    1.09
    ܼ
    1.08
    Ƴ
    1.07
    íč
    1.07
     prétend
    1.05
     toată
    1.03
    ANTES
    1.02
    Activations Density 0.207%

    No Known Activations