© 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. 14159
    Prev
    Next
    INDEX
    Explanations

    conditional whether 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
    u
    3.27
    ا
    2.93
    ির
    2.84
    er
    2.78
    ar
    2.66
    ের
    2.57
    uoj
    2.45
    و
    2.43
    amana
    2.43
    elung
    2.42
    POSITIVE LOGITS
    𝗿
    2.93
    𝗸
    2.82
    ◇
    2.82
    #####
    2.80
    תי
    2.75
    𝗲
    2.69
    ರು
    2.68
    𝘆
    2.62
    Rq
    2.62
    пан
    2.61
    Activations Density 0.011%

    No Known Activations