© 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
    5. 13-GEMMASCOPE-2-RES-65K
    7. 1439
    Prev
    Next
    INDEX
    Explanations

    disclaimer, summary, conclusion

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-1b-pt/resid_post/layer_13_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    सी
    1.23
    cl
    1.13
    hender
    1.09
    m
    1.07
    ado
    1.06
    igar
    1.05
    /
    1.04
    Cn
    1.04
    agem
    1.03
     जगदीश
    1.03
    POSITIVE LOGITS
     derfor
    1.57
     theoretically
    1.38
     därför
    1.38
     hopefully
    1.37
     diciamo
    1.34
    まさに
    1.33
    也就是说
    1.33
    必然
    1.33
     chances
    1.29
     takže
    1.29
    Activations Density 0.858%

    No Known Activations