© 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. 9943
    Prev
    Next
    INDEX
    Explanations

    blood within arteries

    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
    ccionar
    0.51
    Ꮀ
    0.47
    legt
    0.45
    Референце
    0.44
    Ꮘ
    0.41
    Ꮳ
    0.41
    afat
    0.41
    acetamol
    0.40
    jenis
    0.39
    faits
    0.38
    POSITIVE LOGITS
    '
    0.53
     Rules
    0.52
     Nice
    0.48
     homogeneity
    0.48
     Says
    0.48
     Guard
    0.46
     Library
    0.46
     Unfortunately
    0.46
     Allows
    0.46
     Entry
    0.45
    Activations Density 0.001%

    No Known Activations