© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15360
    Prev
    Next
    INDEX
    Explanations

    action, state, or time

    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_31_width_65k_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
     વી
    0.44
     {}
    0.40
     patient
    0.38
     vân
    0.36
     tend
    0.36
     ne
    0.36
    تاة
    0.35
     )
    0.35
     women
    0.35
     associated
    0.35
    POSITIVE LOGITS
    நிலையில்
    0.45
    ர்களையும்
    0.41
    বাংলাদেশের
    0.40
    ლების
    0.39
    ர்களை
    0.39
    しの
    0.39
     बदलने
    0.38
    Meal
    0.38
    বলের
    0.38
     হাজারের
    0.38
    Activations Density 0.006%

    No Known Activations