© 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. 47851
    Prev
    Next
    INDEX
    Explanations

    Electrical Services, shrimp, significantly

    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
    inhas
    0.45
     Jan
    0.42
     idle
    0.42
     insult
    0.42
     ii
    0.42
     inhibit
    0.42
     M
    0.41
     Li
    0.40
    quatre
    0.40
    inhos
    0.40
    POSITIVE LOGITS
    ل
    0.50
    ید
    0.46
    ਤ
    0.46
     ella
    0.46
    দ্র
    0.45
    atically
    0.45
    াকা
    0.44
    یز
    0.44
    ブ
    0.44
    ﾓ
    0.44
    Activations Density 0.001%

    No Known Activations