© 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-16K
    7. 104
    Prev
    Next
    INDEX
    Explanations

    while open

    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
    P
    0.48
     Ос
    0.48
     ich
    0.47
     о
    0.46
     п
    0.44
     ос
    0.43
     Charles
    0.42
    0.41
     по
    0.41
     w
    0.40
    POSITIVE LOGITS
    <unused733>
    0.72
    <unused430>
    0.71
    <unused1201>
    0.70
    <unused1753>
    0.70
     sullen
    0.70
     Palash
    0.69
    <unused570>
    0.69
    <unused1074>
    0.69
    <unused1147>
    0.69
    <unused1148>
    0.68
    Activations Density 0.001%

    No Known Activations