© 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. 40-GEMMASCOPE-2-RES-262K
    7. 193395
    Prev
    Next
    INDEX
    Explanations

    widget extension setup

    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_40_width_262k_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
    蕴
    0.38
    준
    0.37
     `{
    0.36
     πολλ
    0.35
    бир
    0.34
    ült
    0.34
    ujemo
    0.34
    ähn
    0.33
    儼
    0.32
     मर
    0.32
    POSITIVE LOGITS
     carrying
    0.50
     challenging
    0.49
     excitation
    0.48
     warships
    0.44
     exhibition
    0.43
    ંધ
    0.43
    েইল
    0.43
     sportsbook
    0.42
     clickable
    0.41
     redshift
    0.41
    Activations Density 0.000%

    No Known Activations