© 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. 30466
    Prev
    Next
    INDEX
    Explanations

    the other way around

    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
    ל
    0.46
    alama
    0.44
    ـــ
    0.43
    and
    0.42
    ilogue
    0.41
    J
    0.41
    ુ
    0.41
    リ
    0.40
    naden
    0.39
    हिनी
    0.38
    POSITIVE LOGITS
     avenida
    0.44
     pessoas
    0.43
     ageing
    0.43
     vasocon
    0.42
     antioxidants
    0.41
     biodiversity
    0.41
     enzymatic
    0.41
     bloating
    0.41
     anaemia
    0.41
     runny
    0.41
    Activations Density 0.011%

    No Known Activations