© 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. 219964
    Prev
    Next
    INDEX
    Explanations

    countryside subjects

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

    remembering details

    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
    field
    0.46
    tissue
    0.45
    resting
    0.44
    );
    0.42
    داً
    0.42
    {})
    0.41
    âmb
    0.41
    leep
    0.40
    حد
    0.40
    τό
    0.40
    POSITIVE LOGITS
     videolar
    0.61
     éd
    0.58
     alpin
    0.52
     franc
    0.51
    ቪ
    0.51
     était
    0.50
     gero
    0.50
     satir
    0.50
     聞い
    0.50
     ASGI
    0.50
    Activations Density 0.000%

    No Known Activations