© 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. 117235
    Prev
    Next
    INDEX
    Explanations

    small-caps, ligatures, kerning

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

    This neuron detects font‐file header fields and their numeric values (e.g. “Start Char:”, “Encoding:”, and associated numbers).

    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
    なが
    -0.82
     frág
    -0.77
    Pov
    -0.71
    μφωνα
    -0.69
    empleado
    -0.69
     deferred
    -0.69
    模様
    -0.68
    ysh
    -0.68
    striped
    -0.68
    ิ่ม
    -0.68
    POSITIVE LOGITS
     kern
    1.15
     lig
    1.12
     discretionary
    1.11
     ker
    0.98
     Discretion
    0.98
    ker
    0.96
    lig
    0.96
    liga
    0.96
     Lig
    0.95
     liga
    0.95
    Activations Density 0.047%

    No Known Activations