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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 81348
    Prev
    Next
    INDEX
    Explanations

    divisors, glial cells, cosmic, space

    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
     ఉందని
    0.46
     Estudios
    0.45
    aguchi
    0.45
     esti
    0.43
    茎
    0.43
     која
    0.43
    ករ
    0.43
     رجسٹریشن
    0.43
    áció
    0.42
     التى
    0.42
    POSITIVE LOGITS
    a
    0.67
    an
    0.50
     berj
    0.50
    WWW
    0.47
    NORTH
    0.46
    is
    0.46
    z
    0.46
    Pune
    0.45
    p
    0.45
    this
    0.44
    Activations Density 0.002%

    No Known Activations