© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 25461
    Prev
    Next
    INDEX
    Explanations

    two nouns or conjunctions

    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
    সাহিত্য
    0.38
     στη
    0.38
    পাতি
    0.38
    ക
    0.38
    tz
    0.37
    鱔
    0.37
     sedangkan
    0.37
    これにより
    0.37
    ಬಿ
    0.36
    সাহিত
    0.36
    POSITIVE LOGITS
    ar
    0.47
    lipper
    0.46
    Boxes
    0.44
    逦
    0.43
    al
    0.42
     limited
    0.41
     finite
    0.40
     dealing
    0.40
    arın
    0.40
    主机
    0.39
    Activations Density 0.000%

    No Known Activations