© 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. 7-GEMMASCOPE-2-RES-16K
    7. 36
    Prev
    Next
    INDEX
    Explanations

    if clauses

    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_7_width_16k_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
     =========
    0.71
    ERCE
    0.71
    enment
    0.69
     XML
    0.69
     C
    0.68
     غلام
    0.68
    inued
    0.67
     رابط
    0.67
    FromString
    0.67
     Filip
    0.66
    POSITIVE LOGITS
    ңыз
    0.89
    6
    0.89
     debería
    0.87
    4
    0.86
    7
    0.86
    8
    0.84
     deberían
    0.84
    2
    0.80
    3
    0.80
    you
    0.79
    Activations Density 0.899%

    No Known Activations