© 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. 135801
    Prev
    Next
    INDEX
    Explanations

    dates, numbers, and common words

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

    spatial positioning or conditions

    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
     ৃ
    0.49
     ಎ
    0.49
    📤
    0.48
    ৃঙ্খলা
    0.46
    வ்வளவு
    0.46
    sadquotes
    0.46
    ธุรก
    0.45
     याबाबत
    0.45
     효율
    0.45
    😬
    0.45
    POSITIVE LOGITS
     home
    0.47
    ID
    0.46
    トップ
    0.46
     CBL
    0.46
    不
    0.45
    YT
    0.45
    𝐩
    0.45
     top
    0.45
    CBN
    0.44
    ONT
    0.44
    Activations Density 0.001%

    No Known Activations