© 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. 44320
    Prev
    Next
    INDEX
    Explanations

    names and allow/were

    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
     அதிகாரிகள்
    0.52
    Ṕ
    0.51
    ється
    0.50
    É
    0.50
    Բ
    0.49
    ³/
    0.49
    נו
    0.48
    ნა
    0.47
    Ό
    0.47
    П
    0.47
    POSITIVE LOGITS
     Harry
    0.51
     Henry
    0.49
     Jackson
    0.48
     Edmonds
    0.46
     Adam
    0.46
     Phillip
    0.46
     Second
    0.45
     Alice
    0.44
     Hamilton
    0.44
     Seed
    0.44
    Activations Density 0.003%

    No Known Activations