© 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. 17-GEMMASCOPE-2-RES-16K
    7. 13994
    Prev
    Next
    INDEX
    Explanations

    holiday and seasonal words

    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_17_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
    ITECTURE
    2.14
    /-}$
    2.00
    й
    1.96
    ی
    1.90
     midday
    1.87
    varande
    1.76
    いる
    1.63
     semblance
    1.59
     Pada
    1.58
     वाली
    1.57
    POSITIVE LOGITS
    나가
    1.74
    ed
    1.70
    ل
    1.68
    с
    1.62
    用
    1.58
     erase
    1.58
    mine
    1.57
    us
    1.53
    ef
    1.52
    ن
    1.52
    Activations Density 0.046%

    No Known Activations