© 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-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 72409
    Prev
    Next
    INDEX
    Explanations

    want to be

    np_acts-logits-general · gemini-2.5-flash-lite

    text modification including ellipses or omission

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_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
    >.
    0.51
     makeover
    0.46
    utilisateur
    0.45
     gastroenter
    0.43
     journalism
    0.42
     financials
    0.42
     overhauled
    0.41
    桐
    0.41
     revenue
    0.41
     vestibular
    0.40
    POSITIVE LOGITS
     მი
    0.48
    𝐞
    0.46
     रूपों
    0.45
     दिल्‍ली
    0.45
     zug
    0.45
     obiect
    0.45
     डूब
    0.44
    𒉈
    0.44
    сцю
    0.44
     دہ
    0.43
    Activations Density 0.000%

    No Known Activations