© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 1705
    Prev
    Next
    INDEX
    Explanations

    it's

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_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
     ہوتا
    0.22
     gacchati
    0.21
    に行
    0.19
    。
    0.19
    ．
    0.19
     होईल
    0.19
     nějak
    0.19
    َب
    0.19
     gewüns
    0.18
     margarine
    0.18
    POSITIVE LOGITS
     also
    0.33
     также
    0.29
     has
    0.28
     provides
    0.27
     inoltre
    0.27
    also
    0.25
     consists
    0.25
    swering
    0.24
     настолько
    0.24
     therefore
    0.23
    Activations Density 0.520%

    No Known Activations