© 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. 10-GEMMASCOPE-RES-131K
    7. 59003
    Prev
    Next
    INDEX
    Explanations

    about [topic]

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

    The neuron flags the word “About” (as used in the “About X ago” timestamp metadata lines).

    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
     for
    -2.38
     with
    -2.08
    isation
    -2.06
    the
    -1.74
    5
    -1.59
     also
    -1.53
    $
    -1.51
    >
    -1.49
     gdyż
    -1.48
    ;
    -1.46
    POSITIVE LOGITS
     \
    1.70
    崀
    1.69
    綃
    1.60
    鱟
    1.58
    虓
    1.55
     beter
    1.47
    ⾞
    1.46
     them
    1.45
     mö
    1.45
    #*
    1.45
    Activations Density 0.011%

    No Known Activations