© 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. 113392
    Prev
    Next
    INDEX
    Explanations

    daily routine recommendations

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

    roles or states of being

    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
    in
    0.52
    هن
    0.46
    port
    0.46
    y
    0.43
     COMO
    0.43
    aar
    0.42
    мов
    0.42
    Спо
    0.42
    UTH
    0.41
    aéroport
    0.41
    POSITIVE LOGITS
     cotid
    0.55
    䣼
    0.51
     EditText
    0.49
     角
    0.49
     円
    0.48
     pase
    0.48
     sns
    0.47
     piede
    0.47
     データ
    0.47
     বৃদ্ধি
    0.46
    Activations Density 0.000%

    No Known Activations