© 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. 224542
    Prev
    Next
    INDEX
    Explanations

    you followed by verb

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

    aligning yourself

    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
     اختی
    0.48
     galore
    0.45
     statunit
    0.44
    体
    0.43
     nich
    0.42
     sindical
    0.42
    様々な
    0.42
     TextView
    0.41
     cloned
    0.41
     έναν
    0.41
    POSITIVE LOGITS
     instinctively
    0.45
    нят
    0.43
    壑
    0.43
    зии
    0.42
     counterv
    0.42
    voice
    0.42
    Ꮽ
    0.42
     auffi
    0.42
     Verw
    0.41
     Verme
    0.41
    Activations Density 0.001%

    No Known Activations