© 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. 31-GEMMASCOPE-2-RES-262K
    7. 56724
    Prev
    Next
    INDEX
    Explanations

    connects ideas

    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_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
    Ᏺ
    0.52
    దాయ
    0.49
     snar
    0.47
    Bathroom
    0.45
    詓
    0.44
     až
    0.43
     welchem
    0.43
    ()).
    0.43
    彼
    0.43
     FOOT
    0.42
    POSITIVE LOGITS
    orescence
    0.48
     ular
    0.45
    css
    0.44
    opent
    0.44
    op
    0.43
    como
    0.43
    în
    0.43
    risis
    0.43
    com
    0.42
    opot
    0.42
    Activations Density 0.001%

    No Known Activations