© 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
    2. Gemma-3-27B-IT
    3. 31-GEMMASCOPE-2-RES-262K
    4. 108787
    Prev
    Next
    INDEX
    Explanations

    seasoning and salt to taste

    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
     instruct
    0.48
     ideia
    0.47
     инструк
    0.46
     empie
    0.46
     circularly
    0.45
    退
    0.45
     prots
    0.44
    か
    0.44
     taxonomic
    0.44
     approximates
    0.43
    POSITIVE LOGITS
    u
    0.46
     Weight
    0.44
     Length
    0.44
    Peso
    0.44
     長
    0.42
     KMnO
    0.42
    sí
    0.41
     Mél
    0.41
     Sanitation
    0.41
    ".
    0.41
    Activations Density 0.001%

    No Known Activations