© 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. 11205
    Prev
    Next
    INDEX
    Explanations

    pancake recipe

    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
    affiche
    2.96
    newtheorem
    2.83
    startDate
    2.71
    这时候
    2.67
     avis
    2.56
    ד
    2.54
    والفقار
    2.53
    XMLSchema
    2.51
    ről
    2.50
     چرا
    2.49
    POSITIVE LOGITS
    う
    3.87
    et
    3.38
    y
    3.18
    𝕥
    3.10
    ירות
    2.72
    й
    2.72
    as
    2.63
    jLabel
    2.61
    {|
    2.58
    𝕣
    2.57
    Activations Density 0.002%

    No Known Activations