© 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. 212093
    Prev
    Next
    INDEX
    Explanations

    silent options

    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
     kämp
    0.38
     vraie
    0.38
     vutta
    0.38
    福音
    0.37
    場所
    0.37
    rät
    0.37
     übrig
    0.37
    祗
    0.37
     VPN
    0.36
    查找
    0.36
    POSITIVE LOGITS
    haviours
    0.45
     Determination
    0.44
     PLASMA
    0.44
     plasma
    0.43
     Significance
    0.42
     Plasma
    0.41
     वर्गी
    0.40
     Classification
    0.40
    фере
    0.40
     एनालिसिस
    0.39
    Activations Density 0.005%

    No Known Activations