© 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. 40-GEMMASCOPE-2-RES-262K
    7. 36486
    Prev
    Next
    INDEX
    Explanations

    building, step, fear, destination

    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
    ToolTip
    0.40
    delayed
    0.39
    SE
    0.39
     conv
    0.38
    DOS
    0.37
    чиков
    0.37
    ժ
    0.37
    Conv
    0.36
     xii
    0.36
    ৯
    0.36
    POSITIVE LOGITS
     computerScore
    0.42
     عدد
    0.42
     servitude
    0.41
     Schach
    0.40
     Lockhart
    0.40
     sidste
    0.39
     Modell
    0.38
     Logan
    0.38
     لوب
    0.38
     度
    0.37
    Activations Density 0.000%

    No Known Activations