© 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. 206203
    Prev
    Next
    INDEX
    Explanations

    reviewing appeals regarding conditions

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

    optimal, challenging, precise

    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
    种种
    0.58
    ን
    0.53
    পৃ
    0.52
    μεριν
    0.47
     বিষয়
    0.45
    Viz
    0.44
    Ai
    0.43
     причин
    0.43
    rightsquigarrow
    0.43
    雑貨
    0.43
    POSITIVE LOGITS
     especial
    0.52
     delinquent
    0.50
     conto
    0.48
     revising
    0.48
     retorno
    0.46
     recounts
    0.46
     オ
    0.45
     providing
    0.45
     cuenta
    0.45
    rang
    0.45
    Activations Density 0.001%

    No Known Activations