© 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. 72206
    Prev
    Next
    INDEX
    Explanations

    master resident products departure

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

    understands how things work

    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
    u
    0.55
    jz
    0.53
            
    0.51
     책
    0.50
          
    0.48
    liği
    0.47
     bookArray
    0.47
    uç
    0.47
     后
    0.47
    ]*
    0.46
    POSITIVE LOGITS
    プロ
    0.52
    ્રો
    0.51
    โปร
    0.49
     स्टूडियो
    0.48
    Doom
    0.47
     guerrilla
    0.46
     hone
    0.46
     CDP
    0.46
    混凝土
    0.45
    ೇಶ್
    0.44
    Activations Density 0.002%

    No Known Activations