© 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. 108069
    Prev
    Next
    INDEX
    Explanations

    induced change or effect

    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
    撄
    -1.12
     INSTIT
    -0.99
    횃
    -0.98
    nocześnie
    -0.93
     AGRICULTURAL
    -0.92
     usefulness
    -0.91
    嫪
    -0.89
    Incident
    -0.88
    ふわ
    -0.88
     irgende
    -0.86
    POSITIVE LOGITS
     changes
    1.82
     modifications
    1.16
    changes
    1.14
     change
    1.13
     cambios
    1.12
     změ
    1.11
     изменения
    1.10
    變化
    1.05
    Changes
    1.02
     ænd
    1.00
    Activations Density 0.244%

    No Known Activations