© 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. 12415
    Prev
    Next
    INDEX
    Explanations

    the question or answer

    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
     ugl
    1.32
     potrebbero
    1.28
     ぐらい
    1.26
     こう
    1.22
    팬
    1.20
     증가
    1.20
    ახებ
    1.19
     AREAS
    1.18
    碣
    1.18
     팬
    1.17
    POSITIVE LOGITS
     cuenta
    1.09
     misión
    1.08
    .:
    1.07
    后者
    1.07
     estrict
    1.05
    dır
    1.05
    دف
    1.04
     sentencia
    1.03
    ্যান্ড
    1.03
    酩
    1.02
    Activations Density 0.538%

    No Known Activations