© 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. 148662
    Prev
    Next
    INDEX
    Explanations

    business and productivity concepts

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

    active subscription vector matrix interface

    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
     rg
    0.47
     frase
    0.46
     groan
    0.46
     cil
    0.46
    }
    0.45
     bine
    0.44
     fg
    0.44
     FG
    0.44
     Cil
    0.43
     sonra
    0.42
    POSITIVE LOGITS
    lipstick
    0.50
    小物
    0.50
    透过
    0.50
    ِين
    0.47
    傳
    0.47
    ຜ
    0.46
    newValue
    0.45
    websocket
    0.45
    textview
    0.45
    cluster
    0.44
    Activations Density 0.000%

    No Known Activations