© 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. 46724
    Prev
    Next
    INDEX
    Explanations

    api, /

    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
     கதாபாத்திர
    0.44
    прежнему
    0.44
    addEnemy
    0.43
    특히
    0.43
    确实
    0.42
    जगी
    0.42
    щением
    0.42
    境
    0.41
    Ḍ
    0.41
    ता
    0.41
    POSITIVE LOGITS
     Some
    0.51
     Line
    0.48
     noen
    0.48
     Wi
    0.48
     God
    0.45
     (-
    0.45
     four
    0.44
     sunset
    0.44
     Coriolis
    0.44
     its
    0.43
    Activations Density 0.014%

    No Known Activations