© 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. 179224
    Prev
    Next
    INDEX
    Explanations

    attributes, lead, copyright, well, accepted, mathematics, cover

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

    evaluation and standards

    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
     FULL
    0.51
     XNUMX
    0.50
    0.49
    OS
    0.49
    Both
    0.48
    ION
    0.47
    }
    0.46
    CHEMY
    0.46
    FULL
    0.45
     引
    0.45
    POSITIVE LOGITS
     postnatal
    0.47
     tableware
    0.47
     préférences
    0.47
    حدیث
    0.46
    কিন্তু
    0.46
    رويج
    0.45
     favoring
    0.45
    मारक
    0.44
    butanol
    0.44
    टरी
    0.44
    Activations Density 0.001%

    No Known Activations