© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 91080
    Prev
    Next
    INDEX
    Explanations

    code identifiers and paths

    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
    nyttet
    -0.70
    科技
    -0.68
     remote
    -0.68
    足
    -0.66
     Captains
    -0.66
     Mutant
    -0.65
    ̺
    -0.64
     unique
    -0.63
    優勝
    -0.60
     बच्च
    -0.60
    POSITIVE LOGITS
     hijab
    0.77
     turbidity
    0.74
    ród
    0.69
     förb
    0.68
     Plateau
    0.68
    breeding
    0.68
     ఈ
    0.67
     enfermedad
    0.66
    وزش
    0.66
    KindOfClass
    0.66
    Activations Density 0.063%

    No Known Activations