© 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. 144274
    Prev
    Next
    INDEX
    Explanations

    potential solutions

    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
    毀
    0.48
    毁
    0.47
     Sessions
    0.46
     denial
    0.45
     Diet
    0.42
     Stats
    0.42
     Session
    0.42
     diet
    0.42
     čak
    0.41
     Centers
    0.41
    POSITIVE LOGITS
    ීන්
    0.50
    ätz
    0.46
    arla
    0.46
     insectes
    0.45
     öğrenciler
    0.45
    Ꮘ
    0.45
    equations
    0.44
    ᓲ
    0.44
    ፫
    0.44
    чная
    0.43
    Activations Density 0.004%

    No Known Activations