© 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. 156845
    Prev
    Next
    INDEX
    Explanations

    nitrogen-limited state

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

    flexibility, coordinates, things

    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
     eligibility
    0.47
     دان
    0.47
     ಬರುತ್ತ
    0.44
     افضل
    0.44
     選
    0.43
    INotification
    0.43
    尼亚克
    0.43
    general
    0.42
     メガネ
    0.42
     برا
    0.42
    POSITIVE LOGITS
    સ
    0.60
    শিয়া
    0.51
    倫
    0.51
    িকল্প
    0.50
     semana
    0.49
    রোপ
    0.49
     município
    0.48
    স্প
    0.48
    সম্প্রতি
    0.48
    くらい
    0.48
    Activations Density 0.000%

    No Known Activations