© 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. 78556
    Prev
    Next
    INDEX
    Explanations

    future arrangements and plans

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

    academic, jargon, formal, money upfront

    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
     countless
    0.56
     ataupun
    0.54
    ،
    0.49
     maupun
    0.47
     everytime
    0.47
     và
    0.46
     wholeheartedly
    0.46
     jedoch
    0.46
     unsurprisingly
    0.46
    、
    0.46
    POSITIVE LOGITS
    これから
    0.64
     এখনই
    0.58
     готови
    0.57
     сейчас
    0.54
    अब
    0.54
    现在
    0.54
     треба
    0.54
     미리
    0.53
     сега
    0.53
     sekarang
    0.53
    Activations Density 0.009%

    No Known Activations