© 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. 14129
    Prev
    Next
    INDEX
    Explanations

    bow drill

    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
    helps
    1.53
    hill
    1.52
    ushan
    1.52
     {}
    1.52
     valid
    1.51
    idan
    1.51
    ifte
    1.51
    ure
    1.50
     describing
    1.49
     >>
    1.48
    POSITIVE LOGITS
    脏
    2.09
    лекет
    2.02
     inoxyd
    2.01
    รั่ง
    1.99
    lık
    1.99
    anız
    1.97
    Rota
    1.94
    tac
    1.93
    ются
    1.93
    nın
    1.92
    Activations Density 0.000%

    No Known Activations