© 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. 164708
    Prev
    Next
    INDEX
    Explanations

    downhill from

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

    arguing about specific word usage

    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
    வ்வேறு
    0.51
    閬
    0.50
    ℝ
    0.47
    їз
    0.46
    י
    0.46
    𝚝
    0.45
    зо
    0.44
     содержа
    0.44
     сути
    0.44
    ລ
    0.44
    POSITIVE LOGITS
    aupun
    0.50
     Businessman
    0.49
    andeep
    0.49
     Citation
    0.48
     अन्य
    0.47
     UnwrapRef
    0.46
     Would
    0.46
     Jit
    0.45
     よく
    0.45
     argv
    0.44
    Activations Density 0.000%

    No Known Activations