© 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. 2955
    Prev
    Next
    INDEX
    Explanations

    numerical sequences and dates

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

    years

    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
    உங்கள்
    0.41
    আপনার
    0.41
    あなたは
    0.38
     അതിനാ
    0.38
    𝘺
    0.38
    皆さん
    0.37
     सर्वात
    0.37
     आप
    0.37
    आप
    0.37
     முன்னாள்
    0.37
    POSITIVE LOGITS
    ↵
    0.52
    .
    0.44
    ↵↵
    0.41
    ,
    0.38
    -
    0.37
    ;
    0.34
     begon
    0.32
     commence
    0.30
     and
    0.30
     year
    0.30
    Activations Density 0.062%

    No Known Activations