© 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. 133220
    Prev
    Next
    INDEX
    Explanations

    home ideas and kitchen

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

    pine trees

    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
    璈
    0.54
    糇
    0.49
    颢
    0.49
    Muy
    0.48
    牪
    0.48
    કાશ
    0.48
     уров
    0.47
    垲
    0.47
    岧
    0.46
    愀
    0.46
    POSITIVE LOGITS
     pin
    0.61
    pin
    0.53
     Pin
    0.46
    PIN
    0.46
    :
    0.45
     pine
    0.44
     pines
    0.44
     frontline
    0.43
    Pin
    0.41
     pinned
    0.41
    Activations Density 0.001%

    No Known Activations