© 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. 242757
    Prev
    Next
    INDEX
    Explanations

    Vs or disease suffix

    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
    αν
    0.52
     女の子
    0.51
    ATION
    0.50
    コの
    0.45
    rums
    0.44
     सृष्टि
    0.43
     பேசிய
    0.43
     跳
    0.43
     כי
    0.42
    ALITY
    0.42
    POSITIVE LOGITS
     skal
    0.54
    ẃ
    0.52
    停车场
    0.50
    ielten
    0.48
     пребы
    0.47
    暐
    0.47
     Lewandowski
    0.46
    ński
    0.46
     langt
    0.45
    мень
    0.44
    Activations Density 0.000%

    No Known Activations