© 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. 545
    Prev
    Next
    INDEX
    Explanations

    bullet points or quotes

    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
     *
    0.83
     you
    0.80
     it
    0.77
     **
    0.77
     It
    0.76
     كان
    0.71
     If
    0.70
     ي
    0.70
     من
    0.70
     You
    0.69
    POSITIVE LOGITS
    spiritual
    0.88
    environmental
    0.84
    improvement
    0.79
    political
    0.77
    religious
    0.77
    sustainable
    0.77
    importance
    0.77
    regional
    0.77
    evaluation
    0.76
     tranquillity
    0.76
    Activations Density 3.371%

    No Known Activations