© 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-262K
    7. 43866
    Prev
    Next
    INDEX
    Explanations

    ask me anything

    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
    这句话
    0.54
    ști
    0.46
    insulated
    0.45
     बीएड
    0.44
    ᓛ
    0.43
     conversa
    0.42
    relaxation
    0.42
     reprim
    0.41
     прось
    0.41
     dehuman
    0.40
    POSITIVE LOGITS
    內的
    0.46
    常見
    0.45
     選
    0.44
    常用
    0.44
    内
    0.44
     星
    0.43
    常用的
    0.42
     量
    0.41
     主要
    0.41
     ^=
    0.41
    Activations Density 0.001%

    No Known Activations