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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 7-GEMMASCOPE-2-RES-16K
    7. 11915
    Prev
    Next
    INDEX
    Explanations

    refrigerate or refrigeration

    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
    𝚊
    2.28
    꽈
    2.24
    Authors
    2.07
    భ
    2.06
    achy
    2.06
    imat
    1.99
    பந்த
    1.98
    𝙴
    1.97
    ීන්
    1.96
    Articles
    1.96
    POSITIVE LOGITS
    eredReader
    2.43
    ʖ
    2.30
     heml
    2.17
    phants
    2.16
     overlooks
    2.13
    rients
    2.08
     creature
    2.02
     kusal
    1.99
    魎
    1.98
     壁
    1.95
    Activations Density 0.016%

    No Known Activations