© 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. 131695
    Prev
    Next
    INDEX
    Explanations

    they hope

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

    understanding and opening

    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
    督
    0.53
    られています
    0.51
     स्टैट
    0.49
    诤
    0.48
     наре
    0.47
     имена
    0.47
     тер
    0.46
    られて
    0.46
     другими
    0.45
    eker
    0.45
    POSITIVE LOGITS
    荖
    0.42
    Unlock
    0.41
    margin
    0.40
    alay
    0.39
    fur
    0.39
    영어
    0.38
    喎
    0.38
    פשר
    0.38
    uo
    0.38
    song
    0.37
    Activations Density 0.001%

    No Known Activations