© 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. 83876
    Prev
    Next
    INDEX
    Explanations

    content generation restrictions

    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
    tenberg
    0.41
    mig
    0.38
    Miranda
    0.37
    naph
    0.37
    esc
    0.37
    fly
    0.36
    尒
    0.36
    mir
    0.35
    alogy
    0.35
    mik
    0.35
    POSITIVE LOGITS
     bumping
    0.45
    ূনতম
    0.41
     線
    0.40
     fortress
    0.40
     underwriting
    0.40
     biologique
    0.40
     recommendations
    0.40
     marking
    0.39
     luminosity
    0.39
     p
    0.39
    Activations Density 0.000%

    No Known Activations