© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 6993
    Prev
    Next
    INDEX
    Explanations

    words ending in based

    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
    jährige
    0.43
    ۰۰
    0.42
    chool
    0.42
    ossz
    0.40
    ﻤ
    0.40
    ihydro
    0.39
    romatic
    0.39
    kcal
    0.39
    rothed
    0.38
    urname
    0.38
    POSITIVE LOGITS
     be
    0.44
     precision
    0.44
    น
    0.43
     options
    0.42
     influencers
    0.41
     συ
    0.41
     ability
    0.40
     assistance
    0.39
     agreement
    0.39
    ב
    0.39
    Activations Density 0.294%

    No Known Activations