© 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. 180537
    Prev
    Next
    INDEX
    Explanations

    seats, plates, ticket, data, page

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

    belief, sorting, numbers, children, date

    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
     phenotypes
    0.45
     neko
    0.45
     хорошие
    0.43
    ugly
    0.42
    ˟
    0.42
     pit
    0.42
     blockbuster
    0.42
    тэй
    0.41
     самим
    0.41
     dieses
    0.41
    POSITIVE LOGITS
    机场
    0.53
    阃
    0.50
    كين
    0.48
     Azerbai
    0.47
    保
    0.47
    صل
    0.45
    بن
    0.44
    」(
    0.44
    鏢
    0.44
    ⒋
    0.43
    Activations Density 0.000%

    No Known Activations