© 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. 4614
    Prev
    Next
    INDEX
    Explanations

    numbers in crisis lines and ratings

    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
     appBar
    0.25
     groupBox
    0.24
     договору
    0.23
    媤
    0.23
     در
    0.23
     prostit
    0.22
     anagram
    0.22
    gdock
    0.22
    ISPW
    0.22
     Mitarbeit
    0.22
    POSITIVE LOGITS
    0
    0.31
    x
    0.30
    or
    0.29
    o
    0.29
    time
    0.27
    of
    0.26
    he
    0.26
    e
    0.26
    0.26
    3
    0.26
    Activations Density 0.237%

    No Known Activations