© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 90410
    Prev
    Next
    INDEX
    Explanations

    app.use calls

    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
    ]._
    0.44
     restor
    0.44
    ياه
    0.41
     sizz
    0.40
    Nathan
    0.40
     orbits
    0.39
     stressors
    0.39
    Ring
    0.38
    removal
    0.38
     remar
    0.38
    POSITIVE LOGITS
     Χ
    0.43
     εἰ
    0.41
     Darstellung
    0.41
     Trên
    0.40
     Uncomment
    0.38
     voller
    0.38
     บน
    0.38
    赳
    0.38
    kim
    0.38
    ƙ
    0.38
    Activations Density 0.002%

    No Known Activations