© 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. 17-GEMMASCOPE-2-RES-16K
    7. 133
    Prev
    Next
    INDEX
    Explanations

    model response start

    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_17_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
    0.89
     sec
    0.88
     live
    0.83
     —
    0.77
    ?
    0.75
     prime
    0.75
     כ
    0.74
     …
    0.74
     act
    0.74
     already
    0.74
    POSITIVE LOGITS
     masyarakat
    1.49
    Attendees
    1.42
    SystemCall
    1.26
    Residents
    1.24
     walaupun
    1.21
     terlihat
    1.21
    Shan
    1.20
    шымта
    1.20
    <unused2194>
    1.19
     beberapa
    1.19
    Activations Density 0.073%

    No Known Activations