© 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. 1739
    Prev
    Next
    INDEX
    Explanations

    NVMe SSDs

    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
     GUAR
    0.77
    дам
    0.77
     ෆ
    0.74
     동
    0.73
     گو
    0.71
    GUAR
    0.71
     Гор
    0.69
    俣
    0.68
    גל
    0.68
     கா
    0.68
    POSITIVE LOGITS
     token
    0.66
     slits
    0.64
     डीपी
    0.63
     triangles
    0.63
    BLIC
    0.61
     Jeans
    0.59
     pai
    0.59
     tokens
    0.59
     oh
    0.59
     avatars
    0.58
    Activations Density 0.146%

    No Known Activations