© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 91451
    Prev
    Next
    INDEX
    Explanations

    special characters and entities

    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
    1
    0.44
     positive
    0.41
    对于
    0.40
    ].
    0.40
    .]
    0.40
    Bean
    0.40
    ews
    0.40
     positi
    0.39
     decorations
    0.39
    त्रेयी
    0.39
    POSITIVE LOGITS
    വന്‍
    0.50
     శక్తి
    0.50
    ajib
    0.49
     Düsseldorf
    0.48
    疲れ
    0.47
     dajj
    0.46
    スタル
    0.46
    යෙන්
    0.45
    ríamos
    0.44
    咿
    0.44
    Activations Density 0.009%

    No Known Activations