© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 148187
    Prev
    Next
    INDEX
    Explanations

    end of life doulas

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

    code snippets and explanations

    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
     देण्यात
    0.52
    పోయ
    0.51
    லிக்க
    0.51
     loopt
    0.50
    <unused84>
    0.49
     दिखाई
    0.49
     ura
    0.48
    ίκ
    0.48
    接着
    0.48
     conseil
    0.47
    POSITIVE LOGITS
    CAC
    0.48
    ['-
    0.47
    GOT
    0.47
    BN
    0.45
    NEY
    0.45
    Phe
    0.44
    グ
    0.44
    finite
    0.44
    others
    0.44
    OUT
    0.43
    Activations Density 0.000%

    No Known Activations