© 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. 53730
    Prev
    Next
    INDEX
    Explanations

    involved with financial outcomes

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

    size, crates, values, system, image

    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
    ahaman
    0.53
     비해
    0.52
     spectrometry
    0.51
     받았
    0.49
    ن
    0.48
     husbandry
    0.46
    ismar
    0.45
     leeway
    0.45
     기존
    0.45
     dibandingkan
    0.45
    POSITIVE LOGITS
    ForegroundColor
    0.48
    Hướng
    0.47
    Չ
    0.45
    Blo
    0.42
     mè
    0.42
     izgrad
    0.42
    Ք
    0.42
    Chars
    0.41
     bein
    0.41
    Cone
    0.41
    Activations Density 0.000%

    No Known Activations