© 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-3-270M
    5. 15-GEMMASCOPE-2-RES-16K
    7. 1427
    Prev
    Next
    INDEX
    Explanations

    sh followed by names and words

    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
    绅
    1.03
    绷
    0.98
     japonicus
    0.95
    alore
    0.92
    embedding
    0.92
    gfx
    0.92
     navbar
    0.90
     ',
    0.89
     ''.
    0.88
    codon
    0.87
    POSITIVE LOGITS
    Rb
    1.23
    vara
    1.19
     melamine
    1.19
    dmn
    1.18
    fulness
    1.18
    ⑪
    1.17
    tena
    1.17
    託
    1.17
    classed
    1.16
    klassen
    1.15
    Activations Density 0.269%

    No Known Activations