© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 46704
    Prev
    Next
    INDEX
    Explanations

    help hotlines

    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
     महत्त्वा
    0.44
    adoo
    0.42
    കളും
    0.41
     []
    0.41
    www
    0.40
    conf
    0.39
    overnment
    0.39
    government
    0.39
    w
    0.39
    Oregon
    0.38
    POSITIVE LOGITS
     direkt
    0.49
     via
    0.48
     kontakt
    0.47
     contatto
    0.46
     anastomosis
    0.45
     সরাসরি
    0.44
     direttamente
    0.44
     contact
    0.43
     diretamente
    0.42
     receptionist
    0.42
    Activations Density 0.208%

    No Known Activations