© 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-65K
    7. 6810
    Prev
    Next
    INDEX
    Explanations

    competition from

    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_65k_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
     sillons
    0.52
    "+"|".
    0.50
    getMetering
    0.49
    positroid
    0.49
    ፩
    0.49
    navigationItem
    0.49
     大き
    0.48
     composés
    0.48
     აღმასრულებელი
    0.47
    ರುವುದರಿಂದ
    0.47
    POSITIVE LOGITS
     in
    0.59
     to
    0.56
    0.54
    \
    0.54
     *
    0.53
     on
    0.53
     of
    0.52
     -
    0.52
    That
    0.50
     over
    0.50
    Activations Density 0.003%

    No Known Activations