© 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. 41-GEMMASCOPE-2-RES-262K
    7. 988
    Prev
    Next
    INDEX
    Explanations

    "**" followed by role or custom

    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_all/layer_41_width_262k_l0_big
    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
     bhavanti
    0.49
    abhavo
    0.47
     vasena
    0.47
    वतात
    0.46
     gamanam
    0.44
     cittam
    0.43
    끊
    0.43
     congregations
    0.42
     trattano
    0.41
     circuito
    0.41
    POSITIVE LOGITS
     father
    0.44
     secured
    0.44
     slippery
    0.43
     confident
    0.43
     সুরক্ষিত
    0.42
     poppies
    0.42
     protective
    0.41
     shares
    0.41
    %
    0.41
     cracking
    0.40
    Activations Density 0.002%

    No Known Activations