© 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. 130849
    Prev
    Next
    INDEX
    Explanations

    financial and situational contexts

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

    research and management features

    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
    融
    0.57
    اتے
    0.48
    縈
    0.46
     multiplicative
    0.46
    ید
    0.45
    맏
    0.44
    융
    0.44
    탤
    0.43
     mixtures
    0.43
    Expected
    0.42
    POSITIVE LOGITS
     Voj
    0.56
     zahrani
    0.56
    c
    0.54
    čia
    0.53
     horr
    0.52
     Vish
    0.52
    ⊰
    0.51
     chyba
    0.51
    bereich
    0.50
     cuatro
    0.49
    Activations Density 0.000%

    No Known Activations