© 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. 40-GEMMASCOPE-2-RES-262K
    7. 222332
    Prev
    Next
    INDEX
    Explanations

    colors describing visual elements

    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
     curling
    0.40
     состава
    0.39
    StartState
    0.38
     בצ
    0.38
     cataracts
    0.38
    يمه
    0.38
     conceptions
    0.37
    鳶
    0.37
    蕎
    0.37
    𝗋
    0.37
    POSITIVE LOGITS
     annum
    0.43
     (\%)
    0.42
     (>
    0.42
     Unternehmer
    0.41
     Ekonomi
    0.40
    듈
    0.40
     Gaussian
    0.39
    =\
    0.39
     (-)
    0.39
    enture
    0.38
    Activations Density 0.011%

    No Known Activations