© 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. 5097
    Prev
    Next
    INDEX
    Explanations

    past thoughts and anticipation

    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
    初代
    1.23
    ́c
    1.14
    userdata
    1.13
    のではないでしょうか
    1.11
     Messieurs
    1.11
    )}_{
    1.09
    dataType
    1.09
     QUIT
    1.06
    움
    1.04
    ounid
    1.04
    POSITIVE LOGITS
    sono
    1.50
    anta
    1.48
    ходя
    1.45
    jeć
    1.44
    Mostrar
    1.43
    sala
    1.41
    lger
    1.39
    ungsseite
    1.35
    诅
    1.35
     réserve
    1.35
    Activations Density 0.068%

    No Known Activations