© 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. 165895
    Prev
    Next
    INDEX
    Explanations

    speaks at, unless school

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

    eerie halocline

    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
     gå
    0.49
    จัด
    0.48
     తెలియ
    0.47
    府
    0.47
     fest
    0.46
     kole
    0.46
    ไม่
    0.45
    ต้า
    0.45
    จ
    0.45
    使用
    0.45
    POSITIVE LOGITS
    <unused8>
    0.52
    শোধ
    0.51
     નિર્ણ
    0.51
     confuse
    0.48
    month
    0.48
    쁩
    0.48
     ভারতকে
    0.47
    rifugal
    0.47
    ró
    0.46
    ड्यूल
    0.46
    Activations Density 0.000%

    No Known Activations