© 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-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 63109
    Prev
    Next
    INDEX
    Explanations

    noticing that

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

    the presence of numeric tokens (numbers or years) in the text.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
    derdag
    -1.14
    ría
    -1.10
    iciones
    -1.09
    DropTable
    -1.08
    észetes
    -1.06
     gezeigt
    -1.03
    жению
    -1.03
     notion
    -1.01
    FOUND
    -1.00
     unfore
    -0.97
    POSITIVE LOGITS
     that
    1.48
     how
    1.45
    ably
    1.38
     differences
    1.33
     when
    1.33
     changes
    1.30
     something
    1.29
     similarities
    1.20
     adanya
    1.15
     difference
    1.14
    Activations Density 0.028%

    No Known Activations