© 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. 168625
    Prev
    Next
    INDEX
    Explanations

    beyond risk parts riddled

    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
    상을
    0.45
    ప్రదేశ
    0.44
    უცი
    0.44
    bukti
    0.44
    ಸ್ಟ್
    0.44
    脌
    0.44
    იდან
    0.43
    ᓂ
    0.43
    φη
    0.43
     ডেকে
    0.42
    POSITIVE LOGITS
     घ
    0.46
     raus
    0.46
     reh
    0.45
     not
    0.45
     graft
    0.44
     that
    0.44
     rah
    0.44
     pin
    0.44
     cylinder
    0.44
     revisão
    0.44
    Activations Density 0.001%

    No Known Activations