© 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. 31896
    Prev
    Next
    INDEX
    Explanations

    lists of actions or outcomes

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

    practical skills and self-awareness

    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
     約
    0.48
    ေး
    0.47
     Yachts
    0.45
    亿元
    0.45
     Lung
    0.45
     bidang
    0.44
    OrderFlight
    0.44
     Respond
    0.44
     Bean
    0.44
     Jard
    0.44
    POSITIVE LOGITS
     hoo
    0.47
     शेवट
    0.45
    ﺩ
    0.43
    Литература
    0.43
     fighting
    0.43
     factors
    0.43
     frecu
    0.42
     documentary
    0.41
    чается
    0.41
     raiding
    0.41
    Activations Density 0.000%

    No Known Activations