© 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. 80632
    Prev
    Next
    INDEX
    Explanations

    harmful or destructive content

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

    ethnic pride, emissions, end, double 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
    ርሃ
    0.55
    組み立て
    0.54
     மலச்சிக்க
    0.48
    祖
    0.48
    ancia
    0.46
    atura
    0.46
    ौज
    0.45
     metodo
    0.45
    Sans
    0.44
    inputSet
    0.44
    POSITIVE LOGITS
     OBC
    0.49
    ر
    0.47
     NPS
    0.47
     AMC
    0.44
     GBP
    0.44
    त
    0.44
     HCI
    0.44
     థ
    0.43
     EIR
    0.43
    টেড
    0.43
    Activations Density 0.001%

    No Known Activations