© 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-65K
    7. 61834
    Prev
    Next
    INDEX
    Explanations

    patterns related to functions, processes, and descriptions

    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_65k_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
    fficacy
    0.47
     danach
    0.44
     ValueError
    0.42
    vaar
    0.42
    槍
    0.41
     menilai
    0.40
    als
    0.40
    取り
    0.40
    lobin
    0.39
    "),
    0.39
    POSITIVE LOGITS
     canisters
    0.47
    涨
    0.42
    ),]),
    0.41
     parcels
    0.41
     rehearsals
    0.41
     auditions
    0.40
     मोड
    0.40
     totalité
    0.40
    actionBarTab
    0.40
     newMessage
    0.40
    Activations Density 0.015%

    No Known Activations