© 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. 236117
    Prev
    Next
    INDEX
    Explanations

    Wait and slow down

    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
     dined
    0.50
    เซ
    0.49
     ज्य
    0.48
     togetherness
    0.46
    зде
    0.44
    सत्ता
    0.44
    𝓱
    0.43
    ብሰ
    0.42
    ან
    0.42
    ाइड
    0.42
    POSITIVE LOGITS
    ),
    0.52
    )、
    0.52
    )})
    0.49
    kai
    0.49
     iria
    0.48
     bhai
    0.47
    )
    0.47
    urup
    0.47
     yapmak
    0.47
    ">'+
    0.47
    Activations Density 0.000%

    No Known Activations