© 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. 27833
    Prev
    Next
    INDEX
    Explanations

    city-sized or indoor unit

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

    Roomba troubleshooting

    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
    <start_of_image>
    0.43
    Mu
    0.39
    Richard
    0.39
    Nak
    0.38
    Art
    0.38
    »
    0.38
     Che
    0.38
    ब
    0.38
     »
    0.37
    Science
    0.36
    POSITIVE LOGITS
    শৃঙ্খলা
    0.52
    dDevice
    0.52
     drawSprites
    0.51
    एनएल
    0.50
     बीसीजी
    0.49
    showinfo
    0.49
    getDrawable
    0.47
    ånd
    0.47
     ViewBag
    0.46
    ayın
    0.45
    Activations Density 0.000%

    No Known Activations