© 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. 9-GEMMASCOPE-2-RES-262K
    7. 9201
    Prev
    Next
    INDEX
    Explanations

    wishing

    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
    н
    2.80
    യാ
    2.71
    礡
    2.67
     дозво
    2.65
    нэ
    2.63
    tif
    2.61
    לים
    2.60
    ン
    2.56
    eliti
    2.53
    مثل
    2.53
    POSITIVE LOGITS
    𝙡
    3.02
    bone
    2.98
    ся
    2.58
     avis
    2.46
    𝙨
    2.46
    ை
    2.44
     prennent
    2.43
    covery
    2.43
     respectivas
    2.40
    𝙖
    2.38
    Activations Density 0.039%

    No Known Activations