© 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. 99326
    Prev
    Next
    INDEX
    Explanations

    mail away, ontology from, no deposit

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

    harmful content and ethics

    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
    Об
    0.52
     verrà
    0.52
     będzie
    0.51
     سيكون
    0.51
     erlebt
    0.49
    𝗱
    0.48
    Veronica
    0.48
    謂
    0.48
    promotion
    0.48
     inver
    0.47
    POSITIVE LOGITS
     [
    0.49
     Safety
    0.46
    landı
    0.45
     Application
    0.44
     Tu
    0.44
     Types
    0.43
     Catholic
    0.43
     archaeologists
    0.42
     Distributions
    0.42
     Text
    0.41
    Activations Density 0.000%

    No Known Activations