© 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. 34-GEMMASCOPE-RES-131K
    7. 109820
    Prev
    Next
    INDEX
    Explanations

    bottle and following words

    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_34/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
     nue
    -0.96
    السلام
    -0.93
     receita
    -0.92
     milieux
    -0.91
    Connexion
    -0.89
     Militar
    -0.88
     imbued
    -0.88
     vitales
    -0.85
     iva
    -0.85
     croire
    -0.83
    POSITIVE LOGITS
     bottle
    1.36
     Bottle
    1.30
     opener
    1.22
     bottles
    1.19
    bottle
    1.05
    </strong>
    1.01
    cap
    0.98
    Bott
    0.98
    Bottle
    0.96
    andaan
    0.94
    Activations Density 0.010%

    No Known Activations