© 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
    2. Gemma-3-1B-IT
    3. 13-GEMMASCOPE-2-RES-16K
    4. 238
    Prev
    Next
    INDEX
    Explanations

    a fantastic, a viable

    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_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
     is
    0.96
     It
    0.93
     In
    0.92
     this
    0.92
     This
    0.91
     and
    0.90
     it
    0.90
    a
    0.90
    the
    0.89
     And
    0.88
    POSITIVE LOGITS
    徥
    1.16
    徸
    1.15
    <unused497>
    1.13
    <unused315>
    1.11
    <unused1924>
    1.10
    ꘏
    1.10
    webElementXpaths
    1.07
    𒇻
    1.06
    hiqdev
    1.06
    போதும்
    1.06
    Activations Density 1.503%

    No Known Activations