© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 85606
    Prev
    Next
    INDEX
    Explanations

    M. followed by ., call, story

    np_acts-logits-general · gemini-2.5-flash-lite

    MA, EMA, observed, conv

    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
    Negative Logits
    ]">
    0.47
    л
    0.44
    ڑ
    0.43
    p
    0.43
    </h4>
    0.43
    ောင့်
    0.43
    ϲ
    0.42
    fun
    0.42
    ্জ
    0.41
     Salary
    0.41
    POSITIVE LOGITS
     flavonoid
    0.53
     إليها
    0.50
     miš
    0.48
     要求
    0.48
     chromospheres
    0.48
     那麼
    0.48
    鉞
    0.47
    支配
    0.46
     బు
    0.46
     ultrast
    0.46
    Activations Density 0.001%

    No Known Activations