© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 6339
    Prev
    Next
    INDEX
    Explanations

    Metro North

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

    unethical, modus, dot

    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_53_width_65k_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
     Idani
    0.38
    icientes
    0.37
     Salah
    0.36
    ¶
    0.36
    ATIV
    0.36
    }"]
    0.35
    ন্ধ
    0.35
    URUK
    0.35
     javax
    0.34
    𝑏
    0.34
    POSITIVE LOGITS
     ไ
    0.35
    এসই
    0.35
     ಎ
    0.34
    ʼ
    0.34
    ሆነ
    0.33
    འི་
    0.33
    க்கொள்ள
    0.32
    ப்போதும்
    0.32
     romans
    0.31
     να
    0.31
    Activations Density 0.346%

    No Known Activations