© 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. 21240
    Prev
    Next
    INDEX
    Explanations

    strengthening, trainable skills, real estate, TV

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

    approvals, task, change

    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
     פּ
    0.68
     キ
    0.54
     জনগণ
    0.52
     छवि
    0.52
    ჲ
    0.52
     ग़
    0.51
     इज़
    0.51
     वर्कशीट
    0.50
     економі
    0.50
     ی
    0.50
    POSITIVE LOGITS
     TV
    0.52
    दारा
    0.48
     Sax
    0.46
    QUADS
    0.45
     Bernard
    0.44
     Tv
    0.43
     tv
    0.43
    λλ
    0.43
     espe
    0.43
     conv
    0.43
    Activations Density 0.000%

    No Known Activations