© 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. 46937
    Prev
    Next
    INDEX
    Explanations

    phrases ending in specific words

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

    performance metrics and rates

    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
    悪
    0.40
    い
    0.39
     ಮತ್ತೆ
    0.39
     を
    0.37
     nowadays
    0.37
     い
    0.37
    枚举
    0.36
     も
    0.36
     Malay
    0.36
    いろいろ
    0.36
    POSITIVE LOGITS
     সফদর
    0.46
    getAvg
    0.44
    ত্যাশিত
    0.43
    营收
    0.41
    िसोदिया
    0.41
    वीण
    0.41
    ंद्रा
    0.40
    িনবার্গ
    0.40
     महापौर
    0.40
     लक्ष्यों
    0.40
    Activations Density 0.000%

    No Known Activations