© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 53-GEMMASCOPE-2-RES-65K
    7. 2675
    Prev
    Next
    INDEX
    Explanations

    virtualization and tech events

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

    URLs, RAM, data, assessment

    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
     বাঙ
    0.40
    沛
    0.40
     Boss
    0.40
     Bang
    0.39
    邦
    0.39
    坷
    0.39
    UNG
    0.38
    tać
    0.37
    οδο
    0.37
    ปลอด
    0.37
    POSITIVE LOGITS
    Cursor
    0.43
    郵
    0.43
     discern
    0.43
     RMS
    0.43
     lob
    0.42
    rms
    0.42
    HMS
    0.40
    Lob
    0.40
    自治区
    0.39
    รียม
    0.38
    Activations Density 0.000%

    No Known Activations