© 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. 252832
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    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
    ﻫ
    0.46
    κα
    0.45
    5
    0.44
    Payout
    0.43
    போ
    0.43
    _
    0.42
    Spa
    0.41
    ﺠ
    0.41
    יו
    0.41
    ્યુ
    0.40
    POSITIVE LOGITS
     gates
    0.46
    ctuaries
    0.46
     speaks
    0.46
     Bones
    0.46
     sueños
    0.45
     szám
    0.45
     doigts
    0.44
     Rune
    0.44
     berjumpa
    0.44
     fingers
    0.44
    Activations Density 0.002%

    No Known Activations