© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56634
    Prev
    Next
    INDEX
    Explanations

    descriptive follow-ups

    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
    ēl
    0.52
    IRT
    0.50
    ժ
    0.48
    xcschemes
    0.46
    ountain
    0.45
    walten
    0.45
    xRt
    0.44
    Tenn
    0.44
    hika
    0.44
    屇
    0.44
    POSITIVE LOGITS
     conviction
    0.52
     artisanal
    0.52
     trafficking
    0.49
     consistent
    0.48
     aggreg
    0.48
     gros
    0.48
     conced
    0.48
     ridicul
    0.48
     optimisation
    0.48
     indestruct
    0.48
    Activations Density 0.000%

    No Known Activations