© 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. 40-GEMMASCOPE-2-RES-262K
    7. 133092
    Prev
    Next
    INDEX
    Explanations

    date calculation and numbers

    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_40_width_262k_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
    寿命
    0.46
     生活
    0.42
    徝
    0.41
    価値
    0.40
    sistema
    0.40
    ición
    0.40
     circulación
    0.40
    ជីវ
    0.39
    綎
    0.39
     იყოს
    0.39
    POSITIVE LOGITS
    Pointing
    0.38
     ቡ
    0.36
    vere
    0.35
    тивной
    0.34
    름
    0.33
    ราบ
    0.33
     object
    0.32
    apas
    0.32
    lucent
    0.32
    ूक
    0.32
    Activations Density 0.014%

    No Known Activations