© 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. 216809
    Prev
    Next
    INDEX
    Explanations

    office and protection

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

    **(Title, Video, Visual, Social, Sound, Engine, Host) labels

    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
    <0x80>
    0.57
    y
    0.51
    um
    0.50
    0.48
    o
    0.47
    public
    0.47
    UM
    0.46
    }
    0.46
    u
    0.45
    tm
    0.45
    POSITIVE LOGITS
    퐫
    0.52
     পেয়েছিলাম
    0.50
     함수의
    0.50
     історії
    0.49
     uitgen
    0.49
     prefque
    0.49
     függvény
    0.48
    Ფ
    0.48
     ดวง
    0.48
     Ім
    0.47
    Activations Density 0.001%

    No Known Activations