© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 9-GEMMASCOPE-2-RES-16K
    7. 1651
    Prev
    Next
    INDEX
    Explanations

    respond to requests

    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_9_width_16k_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
    ف
    3.38
    teen
    3.02
    ation
    2.95
    ي
    2.93
    জ
    2.81
    ி
    2.76
    પણ
    2.75
    Еще
    2.72
    न
    2.71
    сть
    2.68
    POSITIVE LOGITS
    с
    4.07
     nasa
    2.70
    ார்
    2.70
    ired
    2.63
     flock
    2.61
    نع
    2.60
    𝒋
    2.59
    𝒍
    2.55
    𝒊
    2.52
    𝑨
    2.51
    Activations Density 0.524%

    No Known Activations