© 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. 52253
    Prev
    Next
    INDEX
    Explanations

    thinking about origins

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

    descriptions of altered perceptions

    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
    ɳ
    0.48
     одну
    0.46
     primeras
    0.45
     eventualmente
    0.45
    কন্যা
    0.45
     petróleo
    0.45
    لون
    0.44
     probablement
    0.44
     signatures
    0.43
     profissionais
    0.43
    POSITIVE LOGITS
    Jenis
    0.42
     Sardar
    0.40
    Complaint
    0.40
    Lesson
    0.40
     verstehen
    0.39
    诬
    0.39
     दावा
    0.39
    ését
    0.39
     তাহাদের
    0.39
    Brother
    0.39
    Activations Density 0.000%

    No Known Activations