© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 18607
    Prev
    Next
    INDEX
    Explanations

    words ending in -ton, -inder, -ier

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    (
    0.50
    :
    0.48
    \
    0.45
    的時候
    0.43
    论
    0.41
    的时候
    0.41
    칙
    0.41
    లో
    0.40
     συγκεκρι
    0.40
     대회
    0.40
    POSITIVE LOGITS
    Phir
    0.50
    𐱃
    0.47
    ﻛ
    0.46
    ﻏ
    0.46
     omnis
    0.46
    IIUM
    0.46
     indifferent
    0.45
     unmanned
    0.44
     poesía
    0.44
     Parser
    0.44
    Activations Density 0.007%

    No Known Activations