© 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. 1171
    Prev
    Next
    INDEX
    Explanations

    outlining characteristics and rules

    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
     নেতৃত্বে
    0.67
    ек
    0.63
     Instances
    0.55
    award
    0.55
    tracks
    0.53
    исто
    0.53
     М
    0.53
    选手
    0.52
     Small
    0.52
    각
    0.52
    POSITIVE LOGITS
     pertaining
    0.77
     dotyczące
    0.76
    <unused903>
    0.75
     사항
    0.75
     stemming
    0.74
     indicators
    0.74
    <unused146>
    0.72
     outlined
    0.72
    ensitivity
    0.71
     ofthe
    0.71
    Activations Density 2.907%

    No Known Activations