© 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. 67165
    Prev
    Next
    INDEX
    Explanations

    RM prices and percentages

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

    shareholder reducing shareholding

    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
     নেবার
    0.44
    灶
    0.43
    讹
    0.41
     Subdistrict
    0.40
    𝕦
    0.38
     बटा
    0.38
     सीएच
    0.38
     ইউন
    0.38
    剞
    0.38
     वेद
    0.38
    POSITIVE LOGITS
    prud
    0.47
    Desc
    0.45
    desc
    0.41
     flagged
    0.40
    Perc
    0.40
     prud
    0.40
     સર્
    0.40
    BMP
    0.40
     downturn
    0.39
    Design
    0.39
    Activations Density 0.033%

    No Known Activations