© 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. 14894
    Prev
    Next
    INDEX
    Explanations

    unhexlify, those who, Phil Collins

    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
    rimazole
    2.64
     `
    2.43
    ie
    2.21
     â
    2.13
     감
    2.06
    `
    2.06
    she
    1.99
     ``
    1.98
    ൂട്ട
    1.96
    w
    1.95
    POSITIVE LOGITS
    ization
    2.75
    Та
    2.73
    ᴅ
    2.72
    quantile
    2.71
    getVideo
    2.65
    ations
    2.61
    getConnection
    2.61
    शिव
    2.60
    oksatta
    2.58
    FindBy
    2.58
    Activations Density 0.012%

    No Known Activations