© 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. 109199
    Prev
    Next
    INDEX
    Explanations

    booking a table

    np_acts-logits-general · gemini-2.5-flash-lite

    why, why, advantages, benefits

    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
     TABLE
    0.57
     ALUMIN
    0.49
     GALL
    0.49
     utilizó
    0.48
     raíz
    0.47
    ς
    0.46
    驄
    0.46
    νια
    0.46
     RING
    0.46
    いただいた
    0.46
    POSITIVE LOGITS
    om
    0.47
    lang
    0.46
     حف
    0.45
     vs
    0.44
     Faith
    0.43
    payer
    0.43
     lifeguard
    0.43
     d
    0.42
    herent
    0.42
     تق
    0.42
    Activations Density 0.001%

    No Known Activations