© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 168050
    Prev
    Next
    INDEX
    Explanations

    dynamics from, first true, no background, a single

    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_40_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
     vectorized
    0.40
    ";
    0.38
     filtered
    0.38
     filter
    0.38
     deadly
    0.37
     filtering
    0.36
     faire
    0.35
     Yes
    0.35
     d
    0.35
     Fair
    0.35
    POSITIVE LOGITS
    шов
    0.41
    lesssim
    0.40
    лини
    0.40
     zakres
    0.39
    ூன்
    0.39
    стных
    0.38
    ovski
    0.38
     enthous
    0.38
    Ofer
    0.38
     obstante
    0.38
    Activations Density 0.000%

    No Known Activations