© 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. 73379
    Prev
    Next
    INDEX
    Explanations

    names of places and things

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

    technical features and tools

    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
    ሁሉም
    0.47
    Cit
    0.45
     Fragments
    0.45
    بات
    0.45
    ላይ
    0.44
    ر
    0.44
    Synthetic
    0.43
    Syn
    0.43
    ロス
    0.42
    差
    0.42
    POSITIVE LOGITS
     tedes
    0.55
     vocal
    0.53
     amphibians
    0.51
     locom
    0.50
     viento
    0.50
     dimensiones
    0.50
     campe
    0.49
     Londres
    0.49
     quinze
    0.49
     livre
    0.48
    Activations Density 0.000%

    No Known Activations