© 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. 12-GEMMASCOPE-2-RES-16K
    7. 5149
    Prev
    Next
    INDEX
    Explanations

    stay hydrated

    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_12_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
    -
    1.28
     is
    1.28
    1
    1.25
    ,
    1.13
    2
    1.12
     (
    1.03
     S
    1.01
    like
    1.00
     like
    1.00
    "
    0.95
    POSITIVE LOGITS
     crammed
    2.68
     hapless
    2.64
    Cemento
    2.54
     wondrous
    2.53
     hastily
    2.53
     einst
    2.52
     bitterly
    2.52
     treacherous
    2.51
     pointless
    2.50
    <unused1840>
    2.49
    Activations Density 0.132%

    No Known Activations