© 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-65K
    7. 30152
    Prev
    Next
    INDEX
    Explanations

    contrasting words or phrases

    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_65k_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
     Algorithms
    0.43
     Казино
    0.42
    機場
    0.41
     जन्माष्टमी
    0.41
     attentions
    0.41
    ழுப்பு
    0.40
    㵴
    0.40
     Unavailable
    0.40
    िनियम
    0.40
     Algebras
    0.40
    POSITIVE LOGITS
    :
    0.64
    ៖
    0.50
    :...
    0.46
    ’
    0.44
     vgl
    0.44
     smiled
    0.43
    arcz
    0.43
    ë
    0.43
    DOE
    0.43
    発行
    0.43
    Activations Density 0.011%

    No Known Activations