© 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. 8080
    Prev
    Next
    INDEX
    Explanations

    news and incidents

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

    preventing incidents and crises

    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
     hegemony
    0.51
     supremacy
    0.47
     synthesis
    0.45
    odoxy
    0.44
     Optimization
    0.43
     harmony
    0.42
     Kirch
    0.42
    ᵈ
    0.42
     purified
    0.42
     systematically
    0.41
    POSITIVE LOGITS
     হতাহ
    0.48
    बाइक
    0.46
     ఇటీవల
    0.44
    近年来
    0.44
     সাধারণ
    0.40
     бывают
    0.40
     ­
    0.39
     అంటున్నారు
    0.38
     সাম্প্রতিক
    0.38
     commenters
    0.38
    Activations Density 0.000%

    No Known Activations