© 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. 86498
    Prev
    Next
    INDEX
    Explanations

    sticky interest rates

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

    introducing qualities or states

    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
    사업
    0.52
    도
    0.51
    품
    0.49
    咾
    0.49
    는
    0.49
     نړۍ
    0.48
    조
    0.47
    넬
    0.47
    성화
    0.47
    소서
    0.46
    POSITIVE LOGITS
    h
    0.52
     élevée
    0.47
    pita
    0.46
    sni
    0.46
    tau
    0.46
    wett
    0.44
     inkl
    0.43
     abd
    0.43
    denoted
    0.43
     alkali
    0.43
    Activations Density 0.000%

    No Known Activations