© 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. 22-GEMMASCOPE-2-RES-16K
    7. 10194
    Prev
    Next
    INDEX
    Explanations

    physical posture or position

    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_22_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
    विश्व
    0.96
     রাইফেল
    0.89
    নী
    0.86
     состоя
    0.85
     hare
    0.84
    Бахар
    0.83
    ystone
    0.83
    鷲
    0.81
    かね
    0.81
    скет
    0.80
    POSITIVE LOGITS
    unteer
    1.29
    geç
    1.13
     VV
    1.13
    DICT
    1.13
    vient
    1.11
    quez
    1.08
    uigen
    1.06
    civil
    1.03
    ěz
    1.02
     VB
    1.02
    Activations Density 0.148%

    No Known Activations