© 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. 202206
    Prev
    Next
    INDEX
    Explanations

    loan debt, communities near, corner of

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

    CPU, C1, C0, or day

    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
    ණ
    0.52
    TH
    0.52
    🧉
    0.50
    INGO
    0.49
    ionales
    0.46
    ణాలు
    0.46
     ajouter
    0.45
    nnc
    0.45
    埛
    0.44
    ieso
    0.44
    POSITIVE LOGITS
     oscillator
    0.46
     oscillators
    0.46
     facsimile
    0.45
     processor
    0.43
     desenvolvido
    0.43
     construction
    0.42
     motor
    0.42
    ه‌ی
    0.42
    ovanje
    0.42
    construction
    0.41
    Activations Density 0.000%

    No Known Activations