© 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. 204413
    Prev
    Next
    INDEX
    Explanations

    project, toml, right

    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
     употреб
    0.46
    ЕС
    0.41
    행
    0.41
    사진
    0.41
     Konstru
    0.40
     Chỉ
    0.40
     insoluble
    0.40
     Quais
    0.39
    itis
    0.39
    τής
    0.39
    POSITIVE LOGITS
    เรื่อง
    0.45
     afterlife
    0.44
     aconteceu
    0.43
     sfera
    0.43
     .;
    0.43
     puisque
    0.42
    镰
    0.42
     ブランド
    0.42
    ിക്കു
    0.42
    $/../../../../
    0.42
    Activations Density 0.004%

    No Known Activations