© 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. 74433
    Prev
    Next
    INDEX
    Explanations

    looking for or finding

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

    manipulating these bits

    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
    ⁣
    0.54
     viewHolder
    0.49
     säger
    0.48
     ekran
    0.47
     geeft
    0.47
     idE
    0.46
    ⁣⁣
    0.46
    जनों
    0.45
     welcomes
    0.45
     keram
    0.45
    POSITIVE LOGITS
    though
    0.49
    Divine
    0.47
    ren
    0.47
    tt
    0.46
    ac
    0.46
    apayati
    0.46
     நார்
    0.45
     بجائے
    0.45
    asun
    0.44
    ก
    0.44
    Activations Density 0.002%

    No Known Activations