© 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. 12-GEMMASCOPE-2-RES-16K
    7. 3445
    Prev
    Next
    INDEX
    Explanations

    April dates

    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
     JO
    2.63
     toggle
    2.49
    JO
    2.48
     Reebok
    2.48
     Slob
    2.41
    <0xAD>
    2.40
     gravitational
    2.39
     synth
    2.39
     Phillies
    2.38
    Kick
    2.38
    POSITIVE LOGITS
    諦
    1.07
     undangan
    0.83
    写的
    0.82
    コミュニケーション
    0.80
    那我們
    0.79
    シーズン
    0.79
     vár
    0.79
     ima
    0.74
    罠
    0.74
    等到
    0.74
    Activations Density 0.000%

    No Known Activations