© 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. 1482
    Prev
    Next
    INDEX
    Explanations

    Hebrew vowel points and surrounding text

    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
    .
    0.57
     is
    0.54
    ,
    0.52
     in
    0.52
     to
    0.50
     are
    0.48
    ).
    0.47
    ..
    0.45
     when
    0.45
     will
    0.44
    POSITIVE LOGITS
    Polynucleaires
    0.68
    𒄧
    0.68
     sakamm
    0.68
    <unused5465>
    0.68
    HtIdx
    0.68
    <unused4554>
    0.68
    <unused5514>
    0.68
    <unused4004>
    0.68
    adigane
    0.68
    渦柱
    0.68
    Activations Density 0.000%

    No Known Activations