© 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. 159587
    Prev
    Next
    INDEX
    Explanations

    words followed by punctuation or common words

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

    autoregressive representation

    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
     ඔවුන්
    0.48
    在那
    0.47
     they
    0.47
    ிரம்
    0.46
     tisu
    0.45
     imaju
    0.45
     respuestas
    0.44
    𝙙
    0.44
     muitas
    0.44
     sembra
    0.44
    POSITIVE LOGITS
    Ava
    0.45
    AJ
    0.44
    Contacts
    0.43
    Sur
    0.43
    Anton
    0.42
    合計
    0.41
    娇
    0.41
    Angles
    0.41
    隹
    0.40
    OTAL
    0.40
    Activations Density 0.001%

    No Known Activations