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. 7705
    Prev
    Next
    INDEX
    Explanations

    Academic degrees and titles

    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
     referee
    -0.80
    ahme
    -0.73
    слож
    -0.69
    lynn
    -0.69
     kontroll
    -0.69
     lance
    -0.69
     joystick
    -0.68
     herre
    -0.68
     окру
    -0.67
     scribe
    -0.67
    POSITIVE LOGITS
    すば
    0.76
    rotum
    0.76
    uerdo
    0.72
     เส
    0.69
     toepassing
    0.69
     conservación
    0.68
    ylene
    0.68
     außerhalb
    0.67
    Cedar
    0.66
     farlo
    0.66
    Activations Density 0.027%

    No Known Activations