© 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. 8840
    Prev
    Next
    INDEX
    Explanations

    sales accounted

    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
     borrow
    0.45
     murder
    0.44
     दिवस
    0.43
     patriot
    0.43
     officer
    0.42
    ;
    0.40
     pouvoirs
    0.40
     voices
    0.40
     subordinates
    0.40
     suma
    0.40
    POSITIVE LOGITS
     блю
    0.47
    Take
    0.46
    籽
    0.46
     চৈতন্যের
    0.45
     চৈতন্য
    0.44
     яи
    0.43
    斷
    0.43
    AIM
    0.42
     Wastewater
    0.42
     Maintains
    0.42
    Activations Density 0.001%

    No Known Activations