© 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. 249183
    Prev
    Next
    INDEX
    Explanations

    after her, gentleman, agency

    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
    헝
    0.49
     rapidity
    0.48
     Russie
    0.47
    نامه
    0.47
     fondness
    0.47
     روسیه
    0.46
     différen
    0.46
    絨
    0.46
    ی
    0.45
     domicile
    0.45
    POSITIVE LOGITS
    AN
    0.51
    0
    0.51
     at
    0.49
    SU
    0.49
    :
    0.49
    સુ
    0.48
     Age
    0.47
    Checked
    0.47
     Max
    0.46
     SU
    0.46
    Activations Density 0.000%

    No Known Activations