© 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. 117535
    Prev
    Next
    INDEX
    Explanations

    mountains and countries

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

    is the

    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
    плю
    0.45
    血管
    0.44
    мыс
    0.43
    ຈັດ
    0.42
    敲
    0.42
    ㎜
    0.42
     حافظ
    0.41
    мак
    0.41
     dată
    0.41
    瓣
    0.41
    POSITIVE LOGITS
    ing
    0.51
    ount
    0.48
    )\
    0.48
    othes
    0.48
     opponents
    0.48
    cepter
    0.47
    liga
    0.46
    ല്ലാം
    0.45
     overturn
    0.45
    ord
    0.44
    Activations Density 0.000%

    No Known Activations