© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 12216
    Prev
    Next
    INDEX
    Explanations

    questions, induction descriptions, or specific code sections

    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
     its
    -2.16
     their
    -1.59
     began
    -1.31
     it
    -1.30
     they
    -1.29
     ministro
    -1.23
     within
    -1.16
    Ƕ
    -1.13
     now
    -1.13
     pulsa
    -1.13
    POSITIVE LOGITS
    也可以
    1.14
     Besonders
    1.11
    lya
    1.07
     –
    1.05
    hope
    1.05
    了下去
    1.05
    有一定
    1.05
     Když
    1.03
     asimismo
    1.02
     nordrhein
    1.02
    Activations Density 0.000%

    No Known Activations