© 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. 31-GEMMASCOPE-2-RES-262K
    7. 168666
    Prev
    Next
    INDEX
    Explanations

    often reporting, structured work, low budget

    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
    כר
    0.46
    斜
    0.44
    峰
    0.44
     გან
    0.43
     অধিদ
    0.42
    числе
    0.41
     Premises
    0.41
    مد
    0.41
    刺
    0.40
    漑
    0.40
    POSITIVE LOGITS
     la
    0.49
     layak
    0.47
     l
    0.46
    TI
    0.46
     miedo
    0.44
    🅽
    0.44
    VN
    0.44
     leveraged
    0.44
     servicio
    0.43
    chi
    0.43
    Activations Density 0.005%

    No Known Activations