© 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. 45612
    Prev
    Next
    INDEX
    Explanations

    cut, Family, Kauniainen, comedy, items

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

    instructions or requests

    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
    感じる
    0.53
    ැ
    0.51
     Karen
    0.47
    জিও
    0.46
    受け
    0.46
     Been
    0.45
    รู้สึก
    0.45
    んじゃない
    0.45
     Joanna
    0.44
     Jodi
    0.43
    POSITIVE LOGITS
    вій
    0.45
     forefathers
    0.42
    矩
    0.42
     初始化
    0.42
    btc
    0.42
    匐
    0.41
    ként
    0.40
    bě
    0.40
    біць
    0.39
    Tuple
    0.39
    Activations Density 0.000%

    No Known Activations