© 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. 76809
    Prev
    Next
    INDEX
    Explanations

    code snippets, instructions

    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
    毉
    0.52
    Benzyl
    0.51
    Despatx
    0.49
    überküloz
    0.49
    боль
    0.49
    рость
    0.48
    の為
    0.48
    ٹنے
    0.48
     Мне
    0.47
    рети
    0.46
    POSITIVE LOGITS
    ation
    0.52
     (
    0.52
    {
    0.44
    }$
    0.43
     positive
    0.43
     Florida
    0.43
     |
    0.43
     growth
    0.41
    ných
    0.40
     Tallahassee
    0.40
    Activations Density 0.008%

    No Known Activations