© 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. 212646
    Prev
    Next
    INDEX
    Explanations

    list items and definitions

    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
     mMediaPlayer
    0.41
     машины
    0.40
     doubles
    0.38
    骆
    0.37
    线性
    0.36
    龄
    0.36
     Doubles
    0.36
    发送
    0.35
     getTotal
    0.35
     Ensure
    0.35
    POSITIVE LOGITS
    concerned
    0.47
    关注
    0.42
    nomina
    0.40
    ⇓
    0.40
     توجہ
    0.40
     implicated
    0.39
    痺
    0.38
    contiguous
    0.38
     concerned
    0.38
    ffee
    0.38
    Activations Density 0.000%

    No Known Activations