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. 10-GEMMASCOPE-RES-131K
    4. 218
    Prev
    Next
    INDEX
    Explanations

    paying attention, homage, tribute

    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_10/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
     of
    -1.98
    =
    -1.75
    replyreport
    -1.63
     financiero
    -1.58
    莅
    -1.55
     other
    -1.55
    </i>
    -1.54
    >
    -1.50
    ി
    -1.48
    ;
    -1.47
    POSITIVE LOGITS
    </h4>
    1.89
    </strong>
    1.79
    纡
    1.68
    慥
    1.63
    respuesta
    1.61
    ellä
    1.59
    EXPERIMENTAL
    1.56
     mesmas
    1.53
    meisterschaften
    1.52
    ⅗
    1.52
    Activations Density 0.010%

    No Known Activations