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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 7773
    Prev
    Next
    INDEX
    Explanations

    time stamps 12-hour format

    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
     buque
    -1.10
     cents
    -0.95
    mitteilung
    -0.95
    Denne
    -0.94
     dieß
    -0.94
     bolsillo
    -0.92
    tipe
    -0.91
    knapp
    -0.91
     usta
    -0.91
    erende
    -0.91
    POSITIVE LOGITS
    :
    1.20
     сейчас
    0.92
    je
    0.87
     -->
    0.85
     now
    0.85
     unidentified
    0.85
    мино
    0.84
    ::
    0.84
    hama
    0.82
    ;
    
    0.81
    Activations Density 0.026%

    No Known Activations