© 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. 222732
    Prev
    Next
    INDEX
    Explanations

    specific changes and topics

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

    scene descriptions or structure

    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
    仏
    0.51
     cts
    0.50
    textAllCaps
    0.49
    名の
    0.49
     কা
    0.47
    Translate
    0.46
     hlad
    0.46
    VU
    0.46
    が通販
    0.46
    Ach
    0.45
    POSITIVE LOGITS
    erved
    0.53
    完毕
    0.50
    ק
    0.49
    ivesse
    0.48
     entre
    0.47
    elsk
    0.47
    igen
    0.45
    ب
    0.45
    ivism
    0.45
    arians
    0.44
    Activations Density 0.000%

    No Known Activations