© 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. 238650
    Prev
    Next
    INDEX
    Explanations

    right left and center

    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
     impasse
    0.51
    ടുന്ന
    0.51
    ﻹ
    0.50
     prend
    0.50
     réserve
    0.49
     impulso
    0.49
    并行
    0.49
    யா
    0.48
    𝔞
    0.48
     indeks
    0.47
    POSITIVE LOGITS
     (
    0.47
     করে
    0.47
    rekken
    0.47
     बहनों
    0.46
    cheduler
    0.45
     চলেছে
    0.45
     అధికారులు
    0.44
    、
    0.44
     బె
    0.43
    kij
    0.42
    Activations Density 0.000%

    No Known Activations