© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 219673
    Prev
    Next
    INDEX
    Explanations

    places, characteristics, items

    np_acts-logits-general · gemini-2.5-flash-lite

    craft, resident evil, preserving, seed, year

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Geißler
    0.53
     není
    0.49
    ר
    0.48
     entscheid
    0.47
    刑事
    0.46
    큽
    0.46
    toCharArray
    0.45
    ச்சல்
    0.45
    териа
    0.44
     höhere
    0.44
    POSITIVE LOGITS
     subsections
    0.53
     Switches
    0.53
    Jl
    0.51
    `
    0.50
     перспек
    0.49
    ،
    0.48
     поло
    0.46
     Cycles
    0.46
     pleasurable
    0.46
     Subsection
    0.46
    Activations Density 0.000%

    No Known Activations