© 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. 16162
    Prev
    Next
    INDEX
    Explanations

    specific combinations of words

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

    lists of requirements or reasons

    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
    ){}^
    0.47
    protobuf
    0.43
    りが
    0.43
    。",
    0.42
    ெடு
    0.41
    ijs
    0.41
    ,’’
    0.41
    пущен
    0.40
    ]^
    0.40
    crystal
    0.40
    POSITIVE LOGITS
     واع
    0.51
     whims
    0.50
     florals
    0.50
     especificar
    0.49
     properties
    0.49
     pizz
    0.48
    לח
    0.48
    ထဲ
    0.48
     manejar
    0.47
    압
    0.47
    Activations Density 0.000%

    No Known Activations