© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B-IT
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1213
    Prev
    Next
    INDEX
    Explanations

    duplication or doubling

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-it/resid_post/layer_13_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
     S
    0.58
    0.56
     U
    0.54
      
    0.51
     our
    0.50
     u
    0.50
     the
    0.48
    ளம்
    0.48
     things
    0.48
     i
    0.46
    POSITIVE LOGITS
    𒅊
    1.54
    ꗮ
    1.54
    WMNCA
    1.54
    𒂀
    1.53
    AutoStabilise
    1.53
    HtIdx
    1.53
     vuccatiti
    1.53
    渦柱
    1.53
    𒆝
    1.52
    Polynucleaires
    1.52
    Activations Density 3.913%

    No Known Activations