© 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. 217735
    Prev
    Next
    INDEX
    Explanations

    topics closed or unavailable

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

    not practical or accurate

    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
     I
    0.51
    ecode
    0.46
     criss
    0.44
    parquet
    0.43
     LDS
    0.43
     push
    0.43
     BTS
    0.43
    …
    0.43
     మండ
    0.41
     Latter
    0.41
    POSITIVE LOGITS
     maaaring
    0.50
    变的
    0.50
    खम
    0.48
    Character
    0.48
     chống
    0.48
    SetName
    0.47
    ່ງ
    0.47
    Educ
    0.47
    HIB
    0.46
    தியின்
    0.46
    Activations Density 0.001%

    No Known Activations