© 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. 67455
    Prev
    Next
    INDEX
    Explanations

    technical or descriptive phrases

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

    The neuron activates on the token “Nib” (as in initWithNibName), i.e. references to nib file names in Objective-C code.

    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
     dovuto
    -2.11
     scattata
    -2.09
     Would
    -2.09
    ?”
    -2.06
     vorigen
    -2.05
    婓
    -2.05
     rimasto
    -2.00
     éte
    -1.99
     beschreiben
    -1.95
    زيل
    -1.95
    POSITIVE LOGITS
    ?
    2.81
    [
    2.28
    ),
    2.09
    s
    2.08
    in
    1.98
     redirect
    1.97
    *.
    1.95
    ,
    1.93
     あります
    1.92
    .]
    1.91
    Activations Density 0.000%

    No Known Activations