© 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. 12620
    Prev
    Next
    INDEX
    Explanations

    treating people with others

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

    naming sprints and topics

    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
    のために
    0.41
     إ
    0.41
     ليصل
    0.41
    儩
    0.41
    க்காக
    0.40
    मंत्री
    0.40
     výrob
    0.40
    தைத்
    0.40
    ല്
    0.40
    ことにより
    0.39
    POSITIVE LOGITS
    0.47
     \
    0.36
     behaves
    0.36
     coward
    0.36
    ঠে
    0.35
     Positive
    0.35
     reminded
    0.35
     accusing
    0.35
     empathetic
    0.34
     authoritarian
    0.34
    Activations Density 0.000%

    No Known Activations