© 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. 31-GEMMASCOPE-2-RES-262K
    7. 129012
    Prev
    Next
    INDEX
    Explanations

    Tomorrow at 05:00 AM

    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
    amble
    0.48
    leader
    0.44
    on
    0.44
    regardless
    0.43
    bed
    0.42
    at
    0.42
    、
    0.42
    champ
    0.41
    notlocked
    0.41
     malah
    0.41
    POSITIVE LOGITS
     నొప్పి
    0.47
     rights
    0.46
    竇
    0.45
     direitos
    0.44
    RootDir
    0.44
     права
    0.43
    }`,
    0.43
     therapeut
    0.42
    నర్
    0.42
     droit
    0.42
    Activations Density 0.004%

    No Known Activations