© 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. 14080
    Prev
    Next
    INDEX
    Explanations

    software version updates

    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
    Iddict
    2.15
    <unused1955>
    2.13
     perímetro
    2.12
    🜨
    2.09
    <unused1966>
    2.08
     підпри
    2.07
    <unused1927>
    2.03
    <unused344>
    2.03
    <unused302>
    2.03
    <unused1943>
    2.02
    POSITIVE LOGITS
    a
    1.25
     latest
    1.24
     new
    1.22
     up
    1.17
     then
    1.17
     older
    1.15
    p
    1.13
    an
    1.10
     extended
    1.10
    mitted
    1.07
    Activations Density 0.283%

    No Known Activations