© 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. 243175
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
     tengan
    0.47
     outcast
    0.41
     ذ
    0.41
     خودم
    0.40
    HID
    0.39
     kaug
    0.39
     colloquial
    0.38
    ^{+}$
    0.38
     espiritual
    0.38
     odors
    0.37
    POSITIVE LOGITS
    ess
    0.44
    kale
    0.43
    eluk
    0.42
    ild
    0.42
     статті
    0.40
     adduced
    0.39
    誅
    0.39
    stüt
    0.38
     الثانية
    0.38
    paired
    0.38
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.