© 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-3-1B
    5. 13-GEMMASCOPE-2-RES-16K
    7. 14424
    Prev
    Next
    INDEX
    Explanations

    purpose is

    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
     very
    1.53
     (=
    1.44
    (
    1.43
     completely
    1.41
    completely
    1.37
     (
    1.35
    very
    1.34
    感じで
    1.34
     absolutely
    1.32
    Very
    1.32
    POSITIVE LOGITS
     미래
    1.49
    ᴢ
    1.49
    ^{\#}\
    1.41
    ^{-/-}$
    1.40
    ᵕ
    1.40
    ⧐
    1.40
    anesha
    1.39
     boho
    1.39
     雪
    1.39
    kowej
    1.37
    Activations Density 0.030%

    No Known Activations