© 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. 132092
    Prev
    Next
    INDEX
    Explanations

    pi followed by (

    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
    https
    0.43
     soldered
    0.39
    ចប់
    0.37
    |^{-
    0.37
     nahilalakip
    0.37
     https
    0.37
    会儿
    0.36
    жны
    0.36
     ended
    0.35
    ड़े
    0.35
    POSITIVE LOGITS
    FragmentManager
    0.42
    iam
    0.41
    颉
    0.40
    Utilities
    0.39
    èque
    0.38
     Goethe
    0.38
    Ung
    0.38
    attice
    0.38
    㐱
    0.37
     paran
    0.37
    Activations Density 0.000%

    No Known Activations