© 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. 188711
    Prev
    Next
    INDEX
    Explanations

    daily basis

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

    non-English characters or code

    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
     теркә
    0.57
     frictional
    0.54
     semelhantes
    0.50
    ジ
    0.50
    Ж
    0.49
     voisinage
    0.49
     JEE
    0.49
    କ
    0.49
    ДИ
    0.49
     ці
    0.48
    POSITIVE LOGITS
    an
    0.50
    exists
    0.44
    alb
    0.43
    anym
    0.42
    莉
    0.42
    fony
    0.41
    saved
    0.41
    (“
    0.41
    lette
    0.40
    aney
    0.40
    Activations Density 0.000%

    No Known Activations