© 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-65K
    7. 45927
    Prev
    Next
    INDEX
    Explanations

    or and alternatives

    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
    Př
    0.44
     त्याच
    0.42
     ಅವಕಾಶ
    0.41
     दूसरी
    0.40
    纷纷
    0.40
     نئے
    0.39
    0.39
    ᔕ
    0.39
     त्यो
    0.39
     fleurs
    0.39
    POSITIVE LOGITS
     était
    0.50
     vardı
    0.49
     ήταν
    0.47
     थियो
    0.45
     waren
    0.44
     ছিল
    0.44
     overcame
    0.44
     మాట్లాడుతూ
    0.43
     była
    0.43
     tirelessly
    0.43
    Activations Density 0.020%

    No Known Activations