© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 6617
    Prev
    Next
    INDEX
    Explanations

    high followed by certain words

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    િ
    0.72
    л
    0.68
    始まった
    0.66
    زين
    0.63
    м
    0.63
     posticis
    0.61
    ين
    0.60
    İN
    0.59
    ین
    0.57
    ल
    0.57
    POSITIVE LOGITS
     high
    1.37
    high
    1.27
     High
    1.20
    High
    1.11
    高
    1.08
     HIGH
    1.05
     высоко
    1.00
     גבוה
    0.93
     tinggi
    0.89
    ?
    0.89
    Activations Density 0.148%

    No Known Activations