© 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-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-65K
    7. 4783
    Prev
    Next
    INDEX
    Explanations

    css styling properties

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-4b-it/resid_post/layer_29_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ଲା
    0.85
    PICTOGRAM
    0.84
    MaxIntensity
    0.80
    ograft
    0.78
    engesellschaft
    0.78
    __":
    0.78
    ന്ത്രാ
    0.77
    argmax
    0.76
    idmat
    0.76
    fillText
    0.75
    POSITIVE LOGITS
    :
    1.02
    Bottom
    0.91
     bottom
    0.82
     none
    0.82
    bottom
    0.81
     Bottom
    0.80
     property
    0.76
    Top
    0.76
    none
    0.75
    -
    0.75
    Activations Density 0.087%

    No Known Activations