© 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. 26122
    Prev
    Next
    INDEX
    Explanations

    reasons and explanations

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

    lord, beast, ethylene, numbers, foreign words

    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
     romances
    0.44
    нды
    0.43
    უბ
    0.43
    鄞
    0.43
     libr
    0.41
    తున్నాయి
    0.40
    వారి
    0.39
     precincts
    0.39
    悟空
    0.39
     adventurers
    0.39
    POSITIVE LOGITS
     কেননা
    0.52
    建て
    0.46
     なかっ
    0.45
    rine
    0.45
     karena
    0.44
    哉
    0.43
    ANG
    0.43
     zasad
    0.43
     কারণ
    0.43
     perché
    0.42
    Activations Density 0.000%

    No Known Activations