© 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. 31-GEMMASCOPE-2-RES-262K
    7. 92577
    Prev
    Next
    INDEX
    Explanations

    higher interest, network filtering, automating tasks

    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
    zani
    0.50
     можете
    0.47
    octopus
    0.46
     लीजिए
    0.46
     собира
    0.45
    ▦
    0.45
    ylus
    0.44
    ̴
    0.44
    adá
    0.44
     ['(?
    0.44
    POSITIVE LOGITS
    0.58
     copy
    0.54
     work
    0.50
     dien
    0.50
     cia
    0.50
     present
    0.49
     name
    0.49
     react
    0.47
     caste
    0.47
     park
    0.46
    Activations Density 0.000%

    No Known Activations