© 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. 40-GEMMASCOPE-2-RES-262K
    7. 31551
    Prev
    Next
    INDEX
    Explanations

    path to file location

    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_40_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
     tigris
    0.38
    ivät
    0.38
     मौजूद
    0.37
    ?"
    0.37
    sinya
    0.37
    ័រ
    0.37
    ?".
    0.36
    删
    0.36
    නයේ
    0.36
     ou
    0.35
    POSITIVE LOGITS
     pointing
    0.48
    Pointing
    0.47
    ให้กับ
    0.44
    指向
    0.40
    Caro
    0.40
    Fo
    0.39
    到一个
    0.39
    pointing
    0.38
    зор
    0.38
    Baker
    0.37
    Activations Density 0.009%

    No Known Activations