© 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. 31-GEMMASCOPE-2-RES-262K
    7. 8389
    Prev
    Next
    INDEX
    Explanations

    geometric projections

    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
    anya
    0.42
     Phrases
    0.41
    砵
    0.41
    đena
    0.40
     ++)
    0.39
     باتیں
    0.39
     الحق
    0.39
     растения
    0.38
     있지만
    0.38
    桩
    0.38
    POSITIVE LOGITS
     onto
    0.70
     into
    0.51
     projection
    0.50
     projecting
    0.49
     project
    0.46
     projected
    0.46
     on
    0.46
    Projection
    0.46
     Project
    0.45
     Projection
    0.45
    Activations Density 0.005%

    No Known Activations