© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 1081
    Prev
    Next
    INDEX
    Explanations

    concrete examples, tangible representation

    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
    𐱅
    2.72
     médec
    2.71
    ⠈
    2.57
    ઙ
    2.57
     thisComponent
    2.52
    靗
    2.52
    כּ
    2.52
    𐰢
    2.50
    蚣
    2.48
     Ehnerg
    2.46
    POSITIVE LOGITS
    in
    1.72
     in
    1.67
    is
    1.60
    val
    1.56
    an
    1.49
     at
    1.45
    ↵↵
    1.44
     (
    1.43
    a
    1.42
    on
    1.38
    Activations Density 0.248%

    No Known Activations