© 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 EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 135509
    Prev
    Next
    INDEX
    Explanations

    current state and challenges

    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
     haem
    0.44
    鋆
    0.43
    фа
    0.42
    Ди
    0.42
     Prefeitura
    0.42
     konstit
    0.41
     hormone
    0.41
    Ви
    0.40
     Ви
    0.40
     prostitute
    0.40
    POSITIVE LOGITS
    ථ
    0.53
    ුවන්
    0.49
     “,
    0.48
    めっちゃ
    0.47
    راتكم
    0.47
     माइनस
    0.47
    irthday
    0.46
    homes
    0.46
     lazım
    0.46
    abble
    0.46
    Activations Density 0.001%

    No Known Activations