© 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. 114746
    Prev
    Next
    INDEX
    Explanations

    medical and biological terms

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

    text in programming contexts

    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
     యువ
    0.48
    驹
    0.46
    㹮
    0.46
    শুধ
    0.46
    㠱
    0.45
    úst
    0.45
    东京
    0.45
    美国的
    0.45
    本质
    0.44
    ధిక
    0.44
    POSITIVE LOGITS
     „
    0.54
     duet
    0.46
     dermatitis
    0.45
     c
    0.45
     tyto
    0.45
     tych
    0.44
    lipidemia
    0.44
     nuis
    0.44
     rebirth
    0.44
     B
    0.44
    Activations Density 0.000%

    No Known Activations