© 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. 89936
    Prev
    Next
    INDEX
    Explanations

    agencies and lenders

    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
    bladder
    0.51
    FileInfo
    0.46
    بيق
    0.46
    ramar
    0.45
    Seek
    0.43
    监
    0.43
    恬
    0.43
    ίσ
    0.43
    isierten
    0.43
    िल्ली
    0.42
    POSITIVE LOGITS
    아
    0.46
     manj
    0.45
     Dhar
    0.44
    ತ
    0.44
     IT
    0.43
     indah
    0.43
     indire
    0.43
    उ
    0.43
     ITALY
    0.41
     आवर
    0.41
    Activations Density 0.000%

    No Known Activations