© 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. 415
    Prev
    Next
    INDEX
    Explanations

    physical units

    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
    ing
    0.61
     trading
    0.56
    打
    0.54
     qu
    0.53
     technology
    0.53
    不知
    0.53
     crow
    0.53
     public
    0.52
     single
    0.51
     bon
    0.51
    POSITIVE LOGITS
     mantuvo
    0.90
    ęt
    0.90
     fazendo
    0.89
     speł
    0.89
     enzimas
    0.89
    
    0.89
     شرطونو
    0.88
     apesar
    0.87
     afirmou
    0.86
     ocorreu
    0.86
    Activations Density 0.055%

    No Known Activations