© 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
    2. Gemma-3-27B-IT
    3. 40-GEMMASCOPE-2-RES-262K
    4. 100115
    Prev
    Next
    INDEX
    Explanations

    appearance vs reality

    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
    niku
    0.37
    don
    0.36
    坍
    0.36
    otrex
    0.36
    दस
    0.36
    metadata
    0.35
    ieniem
    0.35
    described
    0.35
    osu
    0.35
    ồm
    0.35
    POSITIVE LOGITS
     termes
    0.48
     barking
    0.40
    强调
    0.39
    付出
    0.39
    पर्य
    0.39
     Jor
    0.38
     snub
    0.38
    거
    0.38
     পারলে
    0.38
    WebView
    0.38
    Activations Density 0.000%

    No Known Activations