© 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. 161966
    Prev
    Next
    INDEX
    Explanations

    common phrases and attributions

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

    following other instructions

    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
    ž
    0.45
    כ
    0.40
     Symbol
    0.40
     Tracks
    0.40
     आयी
    0.40
     ആവശ
    0.40
     After
    0.39
     Between
    0.39
     CRIM
    0.39
     Symmetry
    0.39
    POSITIVE LOGITS
     microbiological
    0.55
     idios
    0.53
     clín
    0.50
     blanchâtre
    0.50
    𒋫
    0.48
     développ
    0.48
    lichting
    0.47
     موسي
    0.47
     développer
    0.47
     ዋና
    0.47
    Activations Density 0.000%

    No Known Activations