© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 211837
    Prev
    Next
    INDEX
    Explanations

    serious topics and codes

    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_40_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
     throws
    0.41
    ----------
    0.41
    null
    0.40
    selected
    0.40
     threw
    0.40
    берг
    0.39
    बरोबर
    0.38
    bgcolor
    0.38
     etch
    0.38
     mirrors
    0.38
    POSITIVE LOGITS
    ⅱ
    0.43
     hijas
    0.43
     dihydro
    0.41
     niños
    0.40
     policía
    0.40
     kecepatan
    0.39
    ⊿
    0.38
    晞
    0.38
     filhos
    0.37
    ✫
    0.37
    Activations Density 0.000%

    No Known Activations