© 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. 24685
    Prev
    Next
    INDEX
    Explanations

    at number

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

    whether or whether

    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
    یدم
    0.45
     همیشه
    0.44
     கொல்ல
    0.43
    時代の
    0.43
    ҉
    0.43
    이야
    0.42
    できる
    0.41
    itura
    0.41
     வாழ்க்கை
    0.40
     પ્રો
    0.40
    POSITIVE LOGITS
    类
    0.50
    偌
    0.49
    ôs
    0.47
    铰
    0.45
    chit
    0.44
    排序
    0.43
     grunds
    0.43
     বর্ত
    0.43
     resultContent
    0.42
    beit
    0.42
    Activations Density 0.000%

    No Known Activations