© 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. 25994
    Prev
    Next
    INDEX
    Explanations

    be taking, enough for, realize that, there is

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

    No, not greater, rejection

    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
     Pleistocene
    0.50
     riche
    0.50
     calm
    0.48
     daff
    0.47
     ’
    0.46
     Wizard
    0.46
     Yeah
    0.46
    ete
    0.46
     seconde
    0.46
     ಕಾಣ
    0.46
    POSITIVE LOGITS
    과
    0.56
    出荷
    0.53
    ब
    0.53
    外
    0.52
     misunderstand
    0.51
    یک
    0.51
     zewnętr
    0.50
    یکی
    0.49
    ड़
    0.49
    اح
    0.49
    Activations Density 0.000%

    No Known Activations