Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12054
    Prev
    Next
    INDEX
    Explanations

    code interpolation

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
     perform
    -1.13
     другие
    -1.09
     других
    -1.05
     anderen
    -1.04
     zwanzig
    -0.98
    nub
    -0.97
     OGSÅ
    -0.94
    lifford
    -0.94
     fünf
    -0.93
     realizó
    -0.93
    POSITIVE LOGITS
     Pediat
    1.24
    although
    1.20
     zodia
    1.13
     Insp
    1.13
     although
    1.07
    Хоро
    1.06
    gunas
    1.05
    Abon
    1.05
     Municip
    1.05
    Kval
    1.05
    Activations Density 0.002%

    No Known Activations