© 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-262K
    7. 11857
    Prev
    Next
    INDEX
    Explanations

    golden retriever or golden hour

    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_262k_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
    ২৮
    2.69
    িং
    2.65
    theorem
    2.58
    ^{\
    2.54
    as
    2.54
    \%
    2.51
    ی
    2.50
    𝑖
    2.48
    𝑡
    2.45
    (\{
    2.44
    POSITIVE LOGITS
    ל
    3.03
    ل
    2.98
    ن
    2.87
    য়
    2.82
    ধ
    2.48
    a
    2.46
    न
    2.46
    য়
    2.46
    ल
    2.45
    ло
    2.33
    Activations Density 0.063%

    No Known Activations