© 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. 32730
    Prev
    Next
    INDEX
    Explanations

    eco-routing, liquid methane, wiper wiring, presidential race

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

    speak about everyone

    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
    ذیر
    0.49
    вари
    0.49
    ྥ
    0.48
    வ்வேறு
    0.48
    аб
    0.48
    法則
    0.48
    الج
    0.47
     சிறு
    0.47
    анали
    0.46
    Чу
    0.46
    POSITIVE LOGITS
    ",
    0.55
    "
    0.51
    ".
    0.51
    ümü
    0.49
     Landing
    0.49
    urr
    0.48
    umen
    0.48
    ungan
    0.48
     "."
    0.47
    ]
    0.47
    Activations Density 0.000%

    No Known Activations