© 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. 161994
    Prev
    Next
    INDEX
    Explanations

    always followed by one of several words

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

    connect, proposal, camp, accum, set

    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
    㕝
    0.49
     оригі
    0.49
    ת
    0.48
    пустить
    0.46
    伀
    0.45
    ============
    0.43
     قرارداد
    0.43
     વ્યક્તિ
    0.43
     بسي
    0.43
    сынын
    0.42
    POSITIVE LOGITS
     Length
    0.52
     sdk
    0.52
     lenght
    0.51
     length
    0.50
     eles
    0.50
     a
    0.49
     Talk
    0.49
     Left
    0.49
     Sardar
    0.49
     Calendar
    0.48
    Activations Density 0.001%

    No Known Activations