© 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. 184513
    Prev
    Next
    INDEX
    Explanations

    legal, financial, and technical descriptions

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

    multi-lingual specific entities

    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
    ма
    0.51
    ः
    0.50
    là
    0.49
     했다
    0.49
    та
    0.48
    на
    0.47
     electr
    0.46
     одна
    0.46
    非洲
    0.45
    В
    0.45
    POSITIVE LOGITS
     deft
    0.47
     ด่า
    0.43
     beden
    0.42
     gebracht
    0.41
     booth
    0.40
     JI
    0.39
     sinners
    0.39
     والاست
    0.39
     genommen
    0.39
     abgerufen
    0.38
    Activations Density 0.001%

    No Known Activations