© 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. 57112
    Prev
    Next
    INDEX
    Explanations

    transition words and phrases

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

    business consultant perspectives

    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
    1
    0.55
     То
    0.45
    3
    0.45
     I
    0.44
    4
    0.42
    7
    0.41
     PRI
    0.41
     nye
    0.41
    決
    0.40
    0
    0.40
    POSITIVE LOGITS
     utilizzato
    0.49
     utilisent
    0.49
     utilizza
    0.47
    <unused2127>
    0.47
     utilisées
    0.47
     পরিবেশ
    0.47
    荣誉
    0.47
     Gebrauch
    0.46
     utilisez
    0.46
    的环境
    0.46
    Activations Density 0.000%

    No Known Activations