© 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. 252157
    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
    giveness
    0.50
    give
    0.43
    ptosis
    0.42
    žeme
    0.41
    ᇁ
    0.41
    imov
    0.40
    gives
    0.40
    給
    0.40
     xmlns
    0.39
    ygons
    0.39
    POSITIVE LOGITS
    ین
    0.44
    klasse
    0.44
     Outback
    0.43
     Erskine
    0.42
     standart
    0.41
     Altitude
    0.41
     Versuch
    0.40
     neke
    0.40
     Haven
    0.39
     خواہش
    0.39
    Activations Density 0.000%

    No Known Activations