© 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. 7754
    Prev
    Next
    INDEX
    Explanations

    numbers, dimensions, or codes

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

    numbers followed by other numbers/symbols

    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
     creditor
    0.27
    িনবার্গ
    0.27
    ه
    0.26
     privat
    0.25
    น้อง
    0.24
     꼭
    0.24
     בע
    0.23
    া
    0.23
     suunn
    0.23
     orgasm
    0.23
    POSITIVE LOGITS
    nd
    0.36
    ení
    0.28
    x
    0.27
    ě
    0.27
    2
    0.26
    ної
    0.26
    ooo
    0.25
    ière
    0.25
    ians
    0.24
    і
    0.24
    Activations Density 0.479%

    No Known Activations