© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 6530
    Prev
    Next
    INDEX
    Explanations

    introduces a name

    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_13_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
    ی
    2.69
    enial
    2.63
    aun
    2.59
    ০
    2.54
    ه
    2.43
    orsement
    2.40
    enay
    2.39
    aż
    2.34
    ン
    2.29
    urias
    2.28
    POSITIVE LOGITS
    bbene
    2.21
    des
    2.19
    lerle
    2.13
    نامه
    2.01
    택
    2.00
    وضع
    1.99
    nya
    1.96
    letzt
    1.94
    heits
    1.93
    Æ
    1.91
    Activations Density 0.714%

    No Known Activations