© 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. 22147
    Prev
    Next
    INDEX
    Explanations

    comparison tables

    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
    ERT
    0.38
     Apro
    0.36
    Modification
    0.36
    Specifically
    0.36
    Employees
    0.36
    ⮚
    0.36
    esta
    0.35
     Subst
    0.35
    Decision
    0.35
    뭍
    0.35
    POSITIVE LOGITS
     instalments
    0.43
     molé
    0.38
     installments
    0.38
     stacks
    0.37
     notches
    0.37
     stér
    0.37
     itineraries
    0.37
     arcane
    0.36
     aé
    0.36
     invern
    0.36
    Activations Density 0.004%

    No Known Activations