© 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. 31-GEMMASCOPE-2-RES-262K
    7. 40099
    Prev
    Next
    INDEX
    Explanations

    legal warnings and consequences

    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_31_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
     ссылку
    0.50
    æ
    0.49
     dwarfs
    0.48
     c
    0.48
     $\
    0.46
     som
    0.46
     slices
    0.46
     sats
    0.46
    á
    0.46
     Dwar
    0.45
    POSITIVE LOGITS
    的
    0.50
    偷
    0.49
    myCollision
    0.47
    漪
    0.46
    )、
    0.45
     AVAudio
    0.45
    生物
    0.45
    ᾖ
    0.44
    更新
    0.43
    脆
    0.43
    Activations Density 0.001%

    No Known Activations