© 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
    2. Gemma-2-27B
    3. 34-GEMMASCOPE-RES-131K
    4. 4197
    Prev
    Next
    INDEX
    Explanations

    revised financial forecast

    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
    jawab
    -0.80
     puissiez
    -0.77
    Dermal
    -0.77
     desaparecer
    -0.77
    豔
    -0.75
     PLEASE
    -0.74
    瞰
    -0.73
     Attempts
    -0.71
     please
    -0.70
    CODEC
    -0.70
    POSITIVE LOGITS
     revised
    2.33
     revision
    2.14
     revising
    2.09
     revise
    1.95
     revisions
    1.94
    revision
    1.79
     lowered
    1.77
    Revision
    1.77
    revised
    1.73
     forecast
    1.71
    Activations Density 0.019%

    No Known Activations