© 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. 41-GEMMASCOPE-2-RES-262K
    7. 389
    Prev
    Next
    INDEX
    Explanations

    Company names and ventures

    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_all/layer_41_width_262k_l0_big
    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
     scena
    0.47
     tenue
    0.44
    地下
    0.43
     patern
    0.43
     حكوم
    0.41
    wendungs
    0.40
    酒
    0.40
     নৈ
    0.40
     potenc
    0.40
     feld
    0.40
    POSITIVE LOGITS
     orientated
    0.44
    yson
    0.43
     dispensed
    0.43
    ছাই
    0.39
     orientado
    0.38
    нні
    0.38
     домаш
    0.37
     scalability
    0.37
    াজার
    0.36
     ").
    0.36
    Activations Density 0.001%

    No Known Activations