© 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. 89407
    Prev
    Next
    INDEX
    Explanations

    specific word followed by pronoun or preposition

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

    I am / I do / I don't

    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
     mith
    0.43
     nauk
    0.43
     gez
    0.42
     motor
    0.41
     meds
    0.41
    ’
    0.41
     emple
    0.40
    အပ်
    0.40
     bont
    0.40
     nutric
    0.39
    POSITIVE LOGITS
     उनका
    0.51
     पवित्र
    0.50
    ポケモン
    0.50
    栯
    0.50
    プレート
    0.49
    残り
    0.49
    ುತ್ತಾರೆ
    0.48
    瞬間
    0.48
    ফোঁ
    0.48
    ठभे
    0.47
    Activations Density 0.000%

    No Known Activations