© 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. 11565
    Prev
    Next
    INDEX
    Explanations

    numbers between 0 and 2

    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
    ではでは
    -1.19
    Sólo
    -1.13
     завжди
    -1.09
    värr
    -1.05
    *);
    -1.05
    hopped
    -1.03
    嗎
    -1.02
    Aquí
    -1.02
    ではまた
    -1.02
     htmlFor
    -1.00
    POSITIVE LOGITS
     несколь
    0.90
     your
    0.90
    担任
    0.90
    INSTALLATION
    0.85
    lığı
    0.84
    rschein
    0.82
    ох
    0.81
    leroi
    0.81
     pics
    0.81
    博物
    0.80
    Activations Density 0.015%

    No Known Activations