© 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. 61
    Prev
    Next
    INDEX
    Explanations

    listing quantities

    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
    0.90
    ,
    0.85
     implicitly
    0.85
     be
    0.83
     at
    0.83
     within
    0.79
     still
    0.79
    :
    0.77
    ?
    0.77
     before
    0.74
    POSITIVE LOGITS
    ５
    1.21
    ４
    1.20
     három
    1.19
    SIX
    1.18
    ８
    1.16
     négy
    1.16
    ３
    1.16
    ７
    1.16
    okatokat
    1.15
    ２
    1.15
    Activations Density 1.119%

    No Known Activations