© 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. 40-GEMMASCOPE-2-RES-16K
    7. 9550
    Prev
    Next
    INDEX
    Explanations

    Stein shipped cultural destructive element

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

    following names or titles

    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_40_width_16k_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
     Ginkuhà
    0.51
    䪱
    0.46
     sic
    0.42
     njega
    0.40
     contar
    0.40
     administrar
    0.39
     puntual
    0.39
     Loại
    0.39
     bir
    0.39
     Subsequently
    0.39
    POSITIVE LOGITS
    筒
    0.37
    ⊡
    0.37
     εξ
    0.37
    ็
    0.36
    を目指
    0.36
    镞
    0.35
    窖
    0.35
    পাতের
    0.35
    ণাস্ত্র
    0.35
    দর্শ
    0.33
    Activations Density 0.244%

    No Known Activations