© 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. 158960
    Prev
    Next
    INDEX
    Explanations

    telephone and support

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

    numbers and division

    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
    对他
    0.47
    েয়
    0.46
     обычно
    0.46
    டுப
    0.44
    مارسة
    0.43
    Ꮿ
    0.43
    给他
    0.42
    頔
    0.42
    दलीय
    0.41
    𒁺
    0.41
    POSITIVE LOGITS
    <
    0.46
     contain
    0.44
     deliver
    0.44
     MAXIMUM
    0.41
     supply
    0.40
        
    0.39
     sprout
    0.38
    含
    0.38
     tast
    0.38
     perfusion
    0.37
    Activations Density 0.001%

    No Known Activations