© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 35880
    Prev
    Next
    INDEX
    Explanations

    af followed by other tokens

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_40_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     भरोसे
    0.39
    щер
    0.39
    Aff
    0.38
    憫
    0.38
    ૢ
    0.37
    딱
    0.36
     поко
    0.36
     딱
    0.36
     percaya
    0.35
     дана
    0.35
    POSITIVE LOGITS
     AF
    0.59
    rikan
    0.51
    Af
    0.49
     af
    0.49
     Af
    0.48
    AF
    0.48
     AFR
    0.46
    af
    0.43
     আফ
    0.43
    দ্
    0.42
    Activations Density 0.002%

    No Known Activations