© 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. 142376
    Prev
    Next
    INDEX
    Explanations

    "you" followed by "so"

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

    dynamical typing or describing comparisons

    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
    トラ
    0.51
    avano
    0.50
    UT
    0.48
    UP
    0.48
    インド
    0.48
    統一
    0.47
    討
    0.47
    シー
    0.46
    umat
    0.46
    投資
    0.45
    POSITIVE LOGITS
     Dynamical
    0.49
     rollerskates
    0.47
     planen
    0.46
    निमल
    0.46
    ؟
    0.45
     pedals
    0.44
    분을
    0.43
    __.
    0.43
    _),
    0.42
    `;
    0.41
    Activations Density 0.001%

    No Known Activations