© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 131204
    Prev
    Next
    INDEX
    Explanations

    handling payments and responsibility

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

    determines calculation results

    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
     photons
    0.50
     viktigt
    0.47
     carvings
    0.45
     이유는
    0.45
     feathers
    0.43
     쌓
    0.43
     inspir
    0.43
     rivulet
    0.43
     indol
    0.42
     formato
    0.42
    POSITIVE LOGITS
    ANE
    0.58
    AND
    0.57
    9
    0.54
    Underv
    0.52
    Land
    0.50
    8
    0.48
    and
    0.45
    AvlTree
    0.45
    也
    0.45
    ORT
    0.44
    Activations Density 0.001%

    No Known Activations