© 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. 220
    Prev
    Next
    INDEX
    Explanations

    a common

    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
    ↵↵
    0.68
    ↵
    0.61
        
    0.57
    seeking
    0.56
    .
    0.55
     considerando
    0.55
     চালায়
    0.54
     Seeking
    0.53
     For
    0.53
     durante
    0.52
    POSITIVE LOGITS
     rất
    0.98
     çok
    0.91
     very
    0.89
     tremendous
    0.88
     quite
    0.87
    <unused2143>
    0.86
     дуже
    0.82
    <unused2183>
    0.82
     incredible
    0.82
     बहुत
    0.82
    Activations Density 3.497%

    No Known Activations