© 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-16K
    7. 10304
    Prev
    Next
    INDEX
    Explanations

    tips for

    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
     এমনকি
    0.48
     hiszen
    0.45
     ಏಕೆಂದರೆ
    0.43
     recompens
    0.43
     basilaires
    0.43
     Spaniard
    0.42
     finalidad
    0.40
    ໍ
    0.40
     FOREIGN
    0.40
     እንዲሁም
    0.40
    POSITIVE LOGITS
     blev
    0.48
     Reliability
    0.45
     Midlands
    0.44
    ade
    0.44
    q
    0.44
    mination
    0.43
    ल्ड
    0.43
     ജില്ലാ
    0.42
    qda
    0.42
    cadilly
    0.41
    Activations Density 0.026%

    No Known Activations