© 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. 31674
    Prev
    Next
    INDEX
    Explanations

    part of the whole

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

    linking concepts

    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
    γά
    0.42
    ագ
    0.39
    獲
    0.39
    राजा
    0.39
    ակ
    0.38
    这将
    0.38
     millions
    0.38
    geti
    0.37
     continuing
    0.37
    driven
    0.37
    POSITIVE LOGITS
     hauptsächlich
    0.48
     있었습니다
    0.47
     تقریباً
    0.47
     전체
    0.46
     संपूर्ण
    0.45
     मुख्यतः
    0.45
    :
    0.45
     원래
    0.45
     பெரும்பாலான
    0.45
     سابق
    0.44
    Activations Density 0.000%

    No Known Activations