© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 69035
    Prev
    Next
    INDEX
    Explanations

    patient safety, package com

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

    variables, constants, or parameters in mathematical expressions.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     to
    -1.24
     خمس
    -1.06
     более
    -1.02
    😞
    -0.93
    😓
    -0.91
    !!!!!!!
    -0.91
    😒
    -0.91
     এবং
    -0.91
     usando
    -0.90
    TONY
    -0.90
    POSITIVE LOGITS
     mindig
    1.07
     some
    1.05
    quinho
    0.95
     eivät
    0.93
    ických
    0.91
     amable
    0.91
    rası
    0.90
     Iowa
    0.89
     voltak
    0.88
     ollut
    0.87
    Activations Density 0.033%

    No Known Activations