© 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. 1812
    Prev
    Next
    INDEX
    Explanations

    freezes the, keeps us

    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
    ي
    1.61
    at
    1.46
    는
    1.41
    ی
    1.41
     der
    1.40
    ing
    1.37
    u
    1.37
    ir
    1.36
    et
    1.31
     Der
    1.30
    POSITIVE LOGITS
    𝐥
    1.71
    ceres
    1.61
    ⤒
    1.49
    <unused1110>
    1.48
    <unused1035>
    1.44
    <unused959>
    1.44
    <unused677>
    1.43
     coveredmethods
    1.43
    <unused945>
    1.41
    <unused162>
    1.40
    Activations Density 0.305%

    No Known Activations