© 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. 118615
    Prev
    Next
    INDEX
    Explanations

    input placeholder appearance

    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
     widow
    -0.87
    ALLENGES
    -0.84
     wording
    -0.80
     bekijken
    -0.79
    reamble
    -0.79
    eces
    -0.77
     ചെയ
    -0.75
    ctos
    -0.75
    colhead
    -0.75
    tites
    -0.74
    POSITIVE LOGITS
     getInput
    0.94
     focus
    0.90
     placeholder
    0.90
    appearance
    0.84
    Placeholder
    0.84
    caret
    0.82
    placeholder
    0.81
     Focus
    0.77
     FormControl
    0.77
    Rounds
    0.75
    Activations Density 0.008%

    No Known Activations