© 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. 199
    Prev
    Next
    INDEX
    Explanations

    here's a breakdown

    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
    ܠܐ
    1.32
    owlapi
    1.31
    fnamefont
    1.30
    鍝
    1.29
    蒾
    1.28
    在地
    1.27
    即便
    1.25
    Settl
    1.21
    媧
    1.20
    IServerGame
    1.20
    POSITIVE LOGITS
    5
    1.59
    8
    1.43
    0
    1.41
    6
    1.37
    9
    1.36
    7
    1.32
    4
    1.29
    a
    1.27
    2
    1.27
    3
    1.26
    Activations Density 0.720%

    No Known Activations