© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 16-GEMMASCOPE-2-RES-262K
    7. 49740
    Prev
    Next
    INDEX
    Explanations

    put up or putting up

    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_16_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
    w
    1.13
    м
    1.00
    𝐬
    0.99
    os
    0.97
    as
    0.96
    es
    0.95
    u
    0.89
    oh
    0.89
    an
    0.84
    m
    0.84
    POSITIVE LOGITS
     realtor
    0.77
     site
    0.76
    Emma
    0.71
    Czech
    0.70
    ﻴ
    0.70
    Ile
    0.68
    Ј
    0.68
    จะ
    0.67
     interfaz
    0.67
    R
    0.66
    Activations Density 0.002%

    No Known Activations