© 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. 23377
    Prev
    Next
    INDEX
    Explanations

    do not endorse or guarantee

    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
     boil
    0.41
    Conventional
    0.39
     conventional
    0.38
    =&
    0.38
    *;
    0.38
     march
    0.38
    IBR
    0.37
    *.
    0.37
    บริ
    0.37
    dison
    0.37
    POSITIVE LOGITS
     Guarantee
    0.49
     garantías
    0.48
     guaranteeing
    0.47
     guarantee
    0.47
     ۋە
    0.47
     гаранти
    0.46
     guarantees
    0.45
     và
    0.45
     garantiza
    0.45
     guarante
    0.45
    Activations Density 0.014%

    No Known Activations