© 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. 121036
    Prev
    Next
    INDEX
    Explanations

    why

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

    stunning visuals

    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
     exos
    0.52
    aku
    0.48
     centr
    0.47
    Relationship
    0.46
     образ
    0.45
    归
    0.45
     elas
    0.44
     esper
    0.44
    رير
    0.44
    ه
    0.44
    POSITIVE LOGITS
    য
    0.51
    ONSE
    0.49
    URCH
    0.48
    ERY
    0.45
    পত্রে
    0.44
     ਯ
    0.44
    ADN
    0.43
     দিয়াছেন
    0.43
     வெளியிட
    0.43
    ÇÕES
    0.43
    Activations Density 0.000%

    No Known Activations