© 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
    2. Gemma-3-1B
    3. 7-GEMMASCOPE-2-RES-16K
    4. 14350
    Prev
    Next
    INDEX
    Explanations

    sound design

    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
    ꗧ
    3.34
    BFAppLink
    3.22
    IServerGame
    3.20
    🖔
    3.20
    𒆞
    3.20
    <unused1399>
    3.17
    㛲
    3.14
    
    3.11
     Creek
    3.11
    𒊍
    3.10
    POSITIVE LOGITS
    gr
    2.27
    뮌
    2.16
     ألمانيا
    2.14
    쾰
    2.12
    strasse
    2.11
    Bundes
    2.07
    kar
    2.03
     독일
    2.00
     Königs
    1.96
     berlin
    1.95
    Activations Density 0.905%

    No Known Activations