© 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. 154808
    Prev
    Next
    INDEX
    Explanations

    obtained, extensions, verbs

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

    approximately equal

    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
    áb
    0.55
    í
    0.54
    eden
    0.50
    áme
    0.50
     recepción
    0.49
     जो
    0.48
    íl
    0.48
    Ⴀ
    0.47
    ely
    0.46
    ást
    0.46
    POSITIVE LOGITS
     head
    0.56
     actinides
    0.55
     enzymes
    0.53
     crabs
    0.52
     eyelashes
    0.51
     extensions
    0.50
     verbs
    0.50
     paragraphs
    0.49
     orchestra
    0.49
     enzyme
    0.48
    Activations Density 0.001%

    No Known Activations