© 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. 51171
    Prev
    Next
    INDEX
    Explanations

    technical terms after code/list markers

    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
     отдельных
    0.42
    త్మిక
    0.42
    naye
    0.42
    ▴
    0.40
    fluent
    0.39
    凭借
    0.38
     примере
    0.38
     نموذ
    0.38
    熟悉
    0.38
    اتی
    0.37
    POSITIVE LOGITS
     glaring
    0.53
     won
    0.51
    uri
    0.46
     Washington
    0.46
     Won
    0.46
     L
    0.43
     Dob
    0.42
     government
    0.42
     fall
    0.41
    usa
    0.41
    Activations Density 0.000%

    No Known Activations

    This feature has no known activations.