© 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-65K
    4. 1296
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    <unused1350>
    1.17
    <unused1354>
    1.12
    <start_of_turn>
    1.11
    <unused832>
    1.10
    屒
    1.09
    䡓
    1.08
    <unused1352>
    1.07
    <unused828>
    1.07
    䀘
    1.07
    <unused1294>
    1.05
    POSITIVE LOGITS
    -
    0.96
    (
    0.96
    /
    0.95
     (
    0.90
    ,
    0.90
     is
    0.79
    )
    0.78
    1
    0.77
    '
    0.75
     adalah
    0.74
    Activations Density 4.305%

    No Known Activations