© 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. 66921
    Prev
    Next
    INDEX
    Explanations

    Follow Back

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

    The neuron is spotting emphatic social-media tokens (like hashtags, all-caps abbreviations, and exclamation-style words) used for emphasis in tweets.

    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
     you
    -1.79
    استان
    -1.38
    雰囲
    -1.27
    blå
    -1.26
     equipaje
    -1.23
    frå
    -1.23
     frança
    -1.23
     spune
    -1.22
    fritt
    -1.21
     Anerkennung
    -1.20
    POSITIVE LOGITS
     to
    2.17
     only
    1.54
    更何况
    1.41
     all
    1.32
     intentando
    1.24
     ExecuteAsync
    1.22
    同じく
    1.20
    ethene
    1.16
    lognese
    1.16
     solely
    1.16
    Activations Density 0.024%

    No Known Activations