© 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. 6301
    Prev
    Next
    INDEX
    Explanations

    entering

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

    in followed by other words

    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
    ]:
    0.54
    ksa
    0.50
     l
    0.49
    D
    0.49
     Reproduced
    0.48
     Instances
    0.48
     Learn
    0.47
    K
    0.47
    '')
    0.46
    S
    0.46
    POSITIVE LOGITS
     vào
    0.75
    هم
    0.71
    进来
    0.69
    ना
    0.67
    进去
    0.67
    入
    0.66
    に入
    0.64
    に入る
    0.60
    ના
    0.60
    ни
    0.59
    Activations Density 0.116%

    No Known Activations