© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 158711
    Prev
    Next
    INDEX
    Explanations

    blind guides, manipulate identifiers, round tables, hire companies

    np_acts-logits-general · gemini-2.5-flash-lite

    list items, titles, or key points

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     agonizing
    0.44
     PyQt
    0.42
     lucrative
    0.42
     amounting
    0.42
    astore
    0.42
     deliciously
    0.42
     termites
    0.41
    킬
    0.41
     billed
    0.40
    꿇
    0.40
    POSITIVE LOGITS
     这
    0.52
     或者
    0.51
    又は
    0.48
     这些
    0.46
     则
    0.46
    呫
    0.46
     veya
    0.46
    或者是
    0.46
     กด
    0.46
     माध्यमा
    0.45
    Activations Density 0.000%

    No Known Activations