© 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. 71875
    Prev
    Next
    INDEX
    Explanations

    contract end

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

    phrase punctuation and specific words

    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
     Verwaltung
    0.55
    rekt
    0.52
     காங்கிரஸ்
    0.51
    inhas
    0.50
    rek
    0.48
     बेरोज
    0.47
    nnet
    0.47
    n
    0.46
    nag
    0.46
     இலங்கை
    0.46
    POSITIVE LOGITS
    サ
    0.62
    速
    0.51
    टी
    0.46
     rápido
    0.45
     速
    0.45
     velocities
    0.44
    カ
    0.44
     stationary
    0.43
    ีย์
    0.43
     sauna
    0.43
    Activations Density 0.001%

    No Known Activations