© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 15015
    Prev
    Next
    INDEX
    Explanations

    definitions, concepts, or specific terms

    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
    ATED
    2.50
    ้าม
    2.37
    sk
    2.24
    ̃
    2.24
     Kangaroo
    2.22
    騨
    2.17
    ipad
    2.15
     %#
    2.15
    нду
    2.13
    아가
    2.12
    POSITIVE LOGITS
     mesure
    2.61
    цам
    2.39
    čka
    2.35
     számos
    2.22
    й
    2.17
    ւ
    2.17
    каде
    2.17
     első
    2.17
     Chub
    2.16
    وٹی
    2.16
    Activations Density 0.000%

    No Known Activations