© 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. 59896
    Prev
    Next
    INDEX
    Explanations

    days of the week

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

    said, again, other languages

    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
    ికె
    0.44
    મી
    0.43
    羰
    0.42
     brains
    0.42
     timeCounter
    0.41
    cB
    0.41
    腾
    0.40
    帅
    0.39
    捏
    0.38
     περισ
    0.38
    POSITIVE LOGITS
     nuovamente
    0.50
     novamente
    0.49
     otra
    0.48
     पुन्हा
    0.47
     ponownie
    0.46
    another
    0.46
    再び
    0.46
     another
    0.45
     nuevamente
    0.45
    organizzazione
    0.44
    Activations Density 0.000%

    No Known Activations