© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 6762
    Prev
    Next
    INDEX
    Explanations

    chmod and dedicate

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-pt/resid_post/layer_15_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
     joyas
    1.12
     atrás
    1.09
    насти
    1.07
     død
    1.04
    cases
    1.04
    벡
    1.03
    حم
    1.02
     partículas
    1.01
    ivní
    1.01
    Category
    1.01
    POSITIVE LOGITS
    簡単に
    1.38
    ountain
    1.34
     %.
    1.29
     Sox
    1.25
    本事
    1.24
    最高的
    1.21
     بسه
    1.18
    teness
    1.18
    例えば
    1.16
    以便
    1.16
    Activations Density 0.067%

    No Known Activations