© 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
    5. 31-GEMMASCOPE-2-RES-262K
    7. 2652
    Prev
    Next
    INDEX
    Explanations

    patterns after keywords

    np_acts-logits-general · gemini-2.5-flash-lite

    concept of shift or change

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ೭
    0.58
    Begriff
    0.56
     את
    0.54
    ת
    0.53
    ೪
    0.53
    Autres
    0.52
    ๘
    0.52
    ๗
    0.52
    츰
    0.52
    ੪
    0.52
    POSITIVE LOGITS
     reimag
    0.54
     infrastructure
    0.52
     immersive
    0.52
     opioid
    0.52
     clinicians
    0.51
     repurposed
    0.49
     multimodal
    0.49
     smartphone
    0.49
     Trump
    0.48
     microbiome
    0.48
    Activations Density 0.032%

    No Known Activations