© 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. 71898
    Prev
    Next
    INDEX
    Explanations

    desires, needs, or descriptions

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

    branch names or configurations

    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
     infotainment
    0.52
     hyperparameters
    0.49
     tequila
    0.48
     ]))
    0.47
     nito
    0.46
     multinationals
    0.46
     kolek
    0.46
     سوم
    0.46
     induk
    0.45
     PARAM
    0.45
    POSITIVE LOGITS
    Circular
    0.46
    报
    0.46
    Nature
    0.46
    nature
    0.45
    life
    0.45
    June
    0.45
    July
    0.44
    వా
    0.43
    Task
    0.43
    так
    0.43
    Activations Density 0.003%

    No Known Activations