© 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. 14315
    Prev
    Next
    INDEX
    Explanations

    yo, check the mic, one two

    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
     abatement
    2.10
     Occurrence
    1.88
    ะ
    1.83
     unbroken
    1.79
    てください
    1.78
    estimation
    1.76
     remainder
    1.75
     aluminium
    1.74
     retailer
    1.73
    eringen
    1.70
    POSITIVE LOGITS
    窕
    2.35
    ดวก
    2.32
     समाजसेवी
    2.29
    Spencer
    2.29
    пыт
    2.27
    romantic
    2.25
    ulman
    2.19
    ری
    2.19
    рь
    2.19
    गोर
    2.13
    Activations Density 0.034%

    No Known Activations