© 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. 6835
    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
    ה
    0.54
     Вен
    0.52
     favoured
    0.52
     Iranian
    0.52
     celebrated
    0.51
    イ
    0.51
    ی
    0.49
    laš
    0.48
    ه
    0.48
     Sağ
    0.47
    POSITIVE LOGITS
    capt
    0.49
    rales
    0.46
    attaa
    0.46
    鋃
    0.45
    Paused
    0.44
    😱
    0.44
    biome
    0.43
    พา
    0.42
    eglasses
    0.42
    rift
    0.42
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.