© 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. 83848
    Prev
    Next
    INDEX
    Explanations

    explaining concepts simply

    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
    ation
    0.55
    support
    0.54
    ā
    0.50
    rae
    0.48
    hed
    0.48
    esség
    0.46
    ess
    0.46
    rees
    0.46
    res
    0.45
    nosis
    0.45
    POSITIVE LOGITS
     victoire
    0.50
     πραγμα
    0.50
    判
    0.49
     nachos
    0.48
     semana
    0.48
     difesa
    0.46
     intercepted
    0.45
     plucked
    0.44
     unas
    0.44
     κάνει
    0.44
    Activations Density 0.003%

    No Known Activations