© 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. 9698
    Prev
    Next
    INDEX
    Explanations

    high + descriptive noun

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

    high followed by quantifiable nouns

    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
    ックレス
    0.52
     Mạnh
    0.51
    ನ್ನಡ
    0.50
    زي
    0.50
     સરળ
    0.49
     Grüße
    0.49
    蚛
    0.49
    زى
    0.48
    ㄅ
    0.48
    িনা
    0.48
    POSITIVE LOGITS
     high
    1.10
    high
    1.08
     גבוה
    0.96
     High
    0.91
     HIGH
    0.88
     tinggi
    0.88
     висо
    0.88
     높은
    0.85
    高
    0.84
    High
    0.83
    Activations Density 0.144%

    No Known Activations