© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56164
    Prev
    Next
    INDEX
    Explanations

    goals and combinations

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Negative Logits
    ION
    0.50
     botched
    0.44
     filmed
    0.43
    न
    0.43
    Authentication
    0.42
     बताए
    0.42
    Ion
    0.41
     തുടങ്ങി
    0.41
    PasswordEncoder
    0.41
    etí
    0.40
    POSITIVE LOGITS
    textt
    0.48
     స్థ
    0.44
     beeld
    0.43
    buffalo
    0.42
    hala
    0.42
     Durchschnitt
    0.42
    ્
    0.42
     gpm
    0.41
     Ziele
    0.41
    heiz
    0.41
    Activations Density 0.002%

    No Known Activations