© 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. 243898
    Prev
    Next
    INDEX
    Explanations

    recorded a, visits to, dosage as, included upfront

    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
    IS
    0.53
    IN
    0.50
    渫
    0.48
    porte
    0.47
    Ở
    0.46
    migrate
    0.46
    empre
    0.44
    ufth
    0.43
    必要的
    0.43
    U
    0.42
    POSITIVE LOGITS
     horrendous
    0.55
     thermonuclear
    0.55
     microturbulence
    0.54
     BWR
    0.53
     waterslide
    0.51
     adoration
    0.48
     ቦታ
    0.48
     symmetrically
    0.48
    ゼン
    0.47
     unitarity
    0.47
    Activations Density 0.000%

    No Known Activations