© 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. 14402
    Prev
    Next
    INDEX
    Explanations

    add details or information

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

    adding or granting access

    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
     बतौर
    0.43
    ]
    0.41
     Bagaimana
    0.39
     कॉम्प
    0.39
     suddenly
    0.38
     %>
    0.37
    Connector
    0.37
     Correspondent
    0.37
    KindOf
    0.37
     would
    0.36
    POSITIVE LOGITS
     postérieure
    0.48
    𒄿
    0.46
     equivari
    0.46
     dialects
    0.44
     granularity
    0.44
     elects
    0.44
     thisStudent
    0.43
     chronology
    0.43
     cohé
    0.42
     rayas
    0.42
    Activations Density 0.000%

    No Known Activations