© 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. 10946
    Prev
    Next
    INDEX
    Explanations

    modifying data structures

    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
    فهام
    2.65
    ل
    2.58
    िंग
    2.56
    as
    2.44
    л
    2.40
    addAlignment
    2.36
     coisa
    2.35
     moy
    2.35
     oo
    2.30
    aviti
    2.28
    POSITIVE LOGITS
    tı
    3.57
    ی
    2.91
    detectChanges
    2.84
    ி
    2.82
    र
    2.80
    sweater
    2.80
    iciary
    2.79
    ा
    2.72
    र्तन
    2.65
     Bessel
    2.64
    Activations Density 0.051%

    No Known Activations