© 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. 150300
    Prev
    Next
    INDEX
    Explanations

    Gambling nj

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

    collocations and sequences

    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
    ޟ
    0.43
     Collision
    0.43
     করিয়৷
    0.42
    ಾಮ
    0.42
     Sensitive
    0.40
     clashed
    0.40
     colliding
    0.40
     Sorting
    0.40
     Updating
    0.40
    ত্য
    0.39
    POSITIVE LOGITS
     nol
    0.52
    irsi
    0.52
    lyPlugin
    0.50
     हैज
    0.50
    㕩
    0.49
    jenja
    0.49
    ného
    0.48
    邺
    0.48
    ritu
    0.48
    izaje
    0.47
    Activations Density 0.001%

    No Known Activations