© 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. 7-GEMMASCOPE-2-RES-16K
    7. 12251
    Prev
    Next
    INDEX
    Explanations

    our answer or solution

    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
    롭
    3.09
    eged
    3.08
    ive
    3.07
    egi
    3.06
    ed
    3.06
    ∬
    3.06
    ка
    3.05
    es
    3.04
    닝
    3.00
    ᴅ
    2.92
    POSITIVE LOGITS
    tion
    2.49
    ्यारह
    2.45
    katapos
    2.42
     बघेल
    2.31
     "}
    2.22
    im
    2.21
    रासत
    2.19
    驒
    2.16
     ogen
    2.13
    til
    2.12
    Activations Density 0.000%

    No Known Activations