© 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-262K
    7. 19514
    Prev
    Next
    INDEX
    Explanations

    smart switch, Baltic Sea

    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_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
     manipulations
    0.48
     frizz
    0.44
    чайно
    0.40
     overlays
    0.40
     ensembles
    0.39
     የቀ
    0.39
    、
    0.38
     mappings
    0.38
     chocol
    0.38
    粖
    0.38
    POSITIVE LOGITS
     This
    0.68
     When
    0.62
     It
    0.61
    2
    0.58
     They
    0.55
    This
    0.54
    3
    0.54
     The
    0.53
     What
    0.53
     In
    0.52
    Activations Density 0.007%

    No Known Activations