© 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. 177311
    Prev
    Next
    INDEX
    Explanations

    diverse spaces

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

    information is displayed

    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
     মোটর
    0.47
    鯨
    0.42
    "(
    0.41
    ouille
    0.41
     NBS
    0.40
     organismo
    0.39
     Kursk
    0.39
     AVL
    0.39
    nahmen
    0.39
    ষ্ঠ
    0.38
    POSITIVE LOGITS
     cooperate
    0.47
    mniej
    0.47
     sighs
    0.45
     heterod
    0.44
    에
    0.43
    DROP
    0.43
    ിക്കാ
    0.43
    لاسه
    0.43
    いに
    0.42
     के
    0.42
    Activations Density 0.001%

    No Known Activations