© 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-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 205182
    Prev
    Next
    INDEX
    Explanations

    options, numbers, lists, or code

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    capability
    0.47
    芘
    0.46
    変
    0.45
    羮
    0.43
    াহ
    0.43
    ě
    0.43
    られる
    0.43
    rial
    0.43
    Assembly
    0.43
    dery
    0.43
    POSITIVE LOGITS
     enquanto
    0.52
     Bal
    0.48
     incred
    0.47
     um
    0.47
     அவருடைய
    0.46
     endroit
    0.45
     buffs
    0.45
     Einst
    0.45
    欳
    0.44
     estándar
    0.44
    Activations Density 0.003%

    No Known Activations