© 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. 38601
    Prev
    Next
    INDEX
    Explanations

    location or state of being

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

    standing still observer

    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
     букмекерлер
    0.45
    为
    0.44
    яви
    0.44
    steacher
    0.44
    ική
    0.43
     用于
    0.43
    onclick
    0.43
     সাধন
    0.42
    还
    0.42
     ঘুর
    0.42
    POSITIVE LOGITS
     stationed
    0.61
     located
    0.57
     perched
    0.54
     situés
    0.53
     hedon
    0.53
     nestled
    0.50
     moored
    0.50
     znajdują
    0.49
     at
    0.49
     situated
    0.48
    Activations Density 0.001%

    No Known Activations