© 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-16K
    7. 7151
    Prev
    Next
    INDEX
    Explanations

    dictionary hash map

    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_16k_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
     for
    0.40
     Ble
    0.35
     also
    0.35
    -
    0.33
    amat
    0.33
     Anatomy
    0.33
     a
    0.31
     to
    0.31
     of
    0.30
     h
    0.30
    POSITIVE LOGITS
     ይህ
    0.36
    endereco
    0.35
    pengaruhi
    0.34
    țit
    0.34
    phed
    0.34
    encript
    0.34
    केंसी
    0.33
    รรค
    0.33
    lessis
    0.33
     によって
    0.33
    Activations Density 0.720%

    No Known Activations