© 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. 14484
    Prev
    Next
    INDEX
    Explanations

    choking while, dry for, overdoses

    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
     antic
    1.73
    efeated
    1.69
     prostaglandins
    1.66
     eradicated
    1.55
     arrested
    1.53
    ❮
    1.53
    setHorizontal
    1.53
     prostaglandin
    1.52
     eliminated
    1.52
     mature
    1.46
    POSITIVE LOGITS
    कालय
    1.63
     ณ
    1.61
     то
    1.61
    itory
    1.59
    рыва
    1.57
     Partial
    1.51
    幅度
    1.49
     Resource
    1.46
     VPC
    1.46
     Brass
    1.46
    Activations Density 0.000%

    No Known Activations