© 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. 66553
    Prev
    Next
    INDEX
    Explanations

    education, food, media, or responsibility

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

    **Order Generation**, **Approval**, **Goal**

    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
    ennium
    0.49
    入手
    0.46
    ब्ब
    0.45
    ब्द
    0.44
    单
    0.43
    টিং
    0.43
    फ्रेंड
    0.42
    絫
    0.42
    نت
    0.42
     rhyth
    0.42
    POSITIVE LOGITS
     հ
    0.49
     டா
    0.49
     দুর্
    0.48
     與
    0.48
     (
    0.48
     সড়
    0.46
     கட்சி
    0.46
     torneo
    0.46
     haut
    0.46
     subjects
    0.45
    Activations Density 0.000%

    No Known Activations