© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 46887
    Prev
    Next
    INDEX
    Explanations

    US B-1B bombers

    np_acts-logits-general · gemini-2.5-flash-lite

    defining concepts and analogies

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    三
    0.43
    本
    0.43
     her
    0.42
     levels
    0.41
    또
    0.41
    只
    0.40
     topography
    0.39
     quiescent
    0.39
    ↵↵↵
    0.39
     کبھی
    0.38
    POSITIVE LOGITS
     kỷ
    0.50
     chàng
    0.50
     आमिर
    0.47
    Blurred
    0.46
    فاعل
    0.46
     जरुरत
    0.45
     prêts
    0.44
    션을
    0.44
     disillusioned
    0.44
    acée
    0.44
    Activations Density 0.000%

    No Known Activations