© 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. 29-GEMMASCOPE-2-RES-65K
    7. 5110
    Prev
    Next
    INDEX
    Explanations

    addition and increments

    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_29_width_65k_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
     Aka
    0.57
    ચે
    0.56
    ︠
    0.55
    Ẻ
    0.55
     UnwrapRef
    0.55
    <0x8D>
    0.55
    വം
    0.54
    தைப்
    0.54
    skine
    0.53
    ؔ
    0.53
    POSITIVE LOGITS
     +
    5.31
    +
    5.29
     plus
    5.12
    plus
    4.64
     Plus
    4.59
    ＋
    4.57
    Plus
    4.48
     $+$
    4.46
     $+
    4.38
    +,
    4.35
    Activations Density 0.844%

    No Known Activations