© 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. 35619
    Prev
    Next
    INDEX
    Explanations

    human rights or vengeance

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

    concepts related to goals and outcomes

    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
    ine
    0.53
    inp
    0.52
    kia
    0.52
    и
    0.51
    ಖ
    0.51
     ২৮
    0.50
    ერთი
    0.50
    ordnet
    0.49
    zäh
    0.49
    isil
    0.49
    POSITIVE LOGITS
     revolutionary
    0.50
     hatred
    0.49
    _{
    0.49
     vengeance
    0.45
    敛
    0.45
     murderous
    0.44
     humiliation
    0.44
     venge
    0.43
    Designed
    0.43
     terrorism
    0.42
    Activations Density 0.000%

    No Known Activations