© 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. 18385
    Prev
    Next
    INDEX
    Explanations

    parameters, price, asset, skills, improving

    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
     lạnh
    0.48
    galactic
    0.48
     なり
    0.46
     मालिक
    0.46
     관심
    0.45
    gget
    0.44
    𝚙
    0.44
     身
    0.44
    given
    0.43
     빌
    0.43
    POSITIVE LOGITS
    ী
    0.50
     Deficiency
    0.46
     deficiency
    0.43
     Cinque
    0.42
    ха
    0.42
    जात
    0.42
    制度
    0.41
     Corne
    0.41
     gradi
    0.41
     Camper
    0.41
    Activations Density 0.002%

    No Known Activations