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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 34-GEMMASCOPE-RES-131K
    7. 77256
    Prev
    Next
    INDEX
    Explanations

    copyright holder rights

    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
    產品
    -0.90
    RTEE
    -0.78
    luia
    -0.78
    actéristique
    -0.77
    ㎥
    -0.76
    waarde
    -0.75
    
    -0.74
    크
    -0.73
    後に
    -0.73
     '':
    -0.73
    POSITIVE LOGITS
     addition
    0.92
    add
    0.84
     =
    0.80
    cution
    0.79
    ⓘ
    0.78
    ोटो
    0.77
     something
    0.77
    addError
    0.76
     aprende
    0.76
     incrementar
    0.76
    Activations Density 0.015%

    No Known Activations