© 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. 135978
    Prev
    Next
    INDEX
    Explanations

    listing features and descriptions

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

    rejecting immigrationessentially prohibits

    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
     unwillingness
    0.52
    ar
    0.50
    _",
    0.49
     unavailability
    0.46
     subsided
    0.45
     stricken
    0.45
     overhe
    0.44
     plunged
    0.44
    aggressive
    0.43
    𝗋
    0.43
    POSITIVE LOGITS
    কাত
    0.54
    Visual
    0.51
    睍
    0.48
    Virus
    0.48
     प्रतिनिधित्व
    0.47
    켓
    0.46
     Vázquez
    0.46
    䔀
    0.46
     حکمت
    0.46
     Cartan
    0.46
    Activations Density 0.001%

    No Known Activations