© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-4B-IT
    5. 29-GEMMASCOPE-2-RES-16K
    7. 1565
    Prev
    Next
    INDEX
    Explanations

    adding or arithmetic

    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_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
    ︠
    0.59
    strnc
    0.56
    <0x8D>
    0.56
     Aka
    0.55
    რობ
    0.52
     рок
    0.52
    シャレ
    0.51
     UnwrapRef
    0.51
    CrossOrigin
    0.51
    कडे
    0.51
    POSITIVE LOGITS
    +
    5.13
     +
    5.12
     plus
    4.71
    ＋
    4.36
    plus
    4.21
     Plus
    4.20
     $+$
    4.19
     $+
    4.18
    Plus
    4.09
    +,
    4.08
    Activations Density 1.233%

    No Known Activations