© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 15773
    Prev
    Next
    INDEX
    Explanations

    required or needed

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     когда
    -1.02
    ervos
    -0.92
     pomiędzy
    -0.85
    After
    -0.85
     after
    -0.82
    เมื่อ
    -0.81
    تي
    -0.80
    意見
    -0.80
    propto
    -0.79
    گوشی
    -0.79
    POSITIVE LOGITS
     required
    1.51
     to
    1.43
     erforderlich
    1.30
     needed
    1.27
    才能
    1.25
     필요
    1.11
     requisite
    1.10
    所需的
    1.08
     Required
    1.07
     potreb
    1.07
    Activations Density 0.064%

    No Known Activations