© 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. 14172
    Prev
    Next
    INDEX
    Explanations

    needs to be done

    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
    ừ
    2.40
    𝐚
    2.24
     ruộng
    2.23
    騨
    2.20
    SizePolicy
    2.12
    Wrapping
    2.11
    Roboto
    2.04
    absch
    2.03
     tratti
    2.02
     trasc
    2.02
    POSITIVE LOGITS
    dinger
    2.16
    nasium
    2.14
     [+
    2.09
    consin
    2.08
    astal
    2.05
    델
    2.02
     fostering
    1.95
     Little
    1.94
    pertension
    1.92
     flourish
    1.92
    Activations Density 0.018%

    No Known Activations