© 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. 125502
    Prev
    Next
    INDEX
    Explanations

    man desires medication

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

    post office or depending on

    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
    چ
    0.48
    ado
    0.48
    il
    0.46
    ul
    0.41
    cess
    0.41
     Ch
    0.40
     Parte
    0.40
    Primer
    0.39
     Kxe
    0.39
     getToken
    0.38
    POSITIVE LOGITS
    ANGMAR
    0.51
     банков
    0.50
    ইডি
    0.49
    𝔬
    0.49
    퍁
    0.49
    ի
    0.49
    般
    0.48
    㡚
    0.48
    𝗇
    0.48
    ℍ
    0.48
    Activations Density 0.000%

    No Known Activations