© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 60742
    Prev
    Next
    INDEX
    Explanations

    SS followed by initials or names

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

    The neuron fires on occurrences of the token “SS” immediately followed by a numeric code (e.g. “SS 362,” “SS 286,” “SS 356,” etc.).

    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
    .
    -3.80
    獁
    -2.77
     tradis
    -2.16
    ⤦
    -2.08
    وئ
    -2.08
    锇
    -2.06
     Guitars
    -2.05
     mutta
    -2.03
    kommt
    -2.02
    Dette
    -2.02
    POSITIVE LOGITS
    ).
    2.44
     methodologies
    2.38
     è
    2.33
     aña
    2.30
     continúas
    2.27
     ganze
    2.19
     impec
    2.17
    
    2.16
     eer
    2.16
    那你
    2.14
    Activations Density 0.007%

    No Known Activations