© 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. 32680
    Prev
    Next
    INDEX
    Explanations

    describing composition or membership

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

    consists of parts

    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
    سازی
    0.61
     možnost
    0.57
     возможность
    0.52
    กรณี
    0.52
     zmiany
    0.52
     yerden
    0.51
    فى
    0.50
    h
    0.49
    bidden
    0.49
     ہمارا
    0.48
    POSITIVE LOGITS
     terdiri
    1.06
     consists
    1.04
     consisting
    1.04
     comprised
    1.02
     consisted
    1.02
     består
    0.96
     consist
    0.93
     composed
    0.93
     comprises
    0.93
     comprising
    0.91
    Activations Density 0.040%

    No Known Activations