© 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. 120381
    Prev
    Next
    INDEX
    Explanations

    find that / remember that / end of

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

    efficiency expert

    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
    yorum
    0.52
    gericht
    0.52
     benefitted
    0.50
     benefited
    0.49
    hoe
    0.48
    tidak
    0.47
    zovaniyu
    0.47
    z
    0.46
    tere
    0.46
    ced
    0.44
    POSITIVE LOGITS
    ोजन
    0.51
     needles
    0.48
     our
    0.47
     necklaces
    0.47
    學
    0.46
     various
    0.46
     troughs
    0.45
    諸
    0.45
     nails
    0.44
     transistors
    0.44
    Activations Density 0.001%

    No Known Activations