© 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. 479
    Prev
    Next
    INDEX
    Explanations

    common practice

    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
     TNumber
    1.75
    通知
    1.68
     pontos
    1.61
    𒊩
    1.61
    惀
    1.60
     reconocida
    1.59
     zvý
    1.58
     význam
    1.57
    对应的
    1.57
     rimane
    1.57
    POSITIVE LOGITS
    ness
    1.68
    ly
    1.36
    nesses
    1.22
    ependent
    1.16
    amaged
    1.13
    ten
    1.09
    ry
    1.08
    d
    1.03
    nesse
    1.02
    dy
    1.00
    Activations Density 3.340%

    No Known Activations