© 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. 3013
    Prev
    Next
    INDEX
    Explanations

    is a, is one, so

    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
    éns
    0.45
     කරයි
    0.42
    该
    0.41
     Combs
    0.40
     voire
    0.40
     Nä
    0.39
     dito
    0.39
     Roberts
    0.38
    umbling
    0.38
     该
    0.38
    POSITIVE LOGITS
     настолько
    0.67
     മാത്രമല്ല
    0.51
     tellement
    0.50
     लोकप्रियता
    0.46
    だけでなく
    0.44
    作为一个
    0.43
     undeniably
    0.43
     unquestionably
    0.43
     மட்டுமல்ல
    0.43
     originalmente
    0.42
    Activations Density 0.439%

    No Known Activations