© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 33391
    Prev
    Next
    INDEX
    Explanations

    tape and related compounds

    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
    ک
    0.51
    ีย์
    0.45
    ラー
    0.43
    ು
    0.43
     disebut
    0.42
    ダム
    0.42
    य
    0.41
    ਾਸ
    0.40
     dàng
    0.39
    বার্গ
    0.39
    POSITIVE LOGITS
    Tape
    0.88
     tape
    0.87
    tape
    0.84
     Tape
    0.82
     tapes
    0.70
    stap
    0.64
     staple
    0.63
    テープ
    0.62
     staples
    0.58
     taped
    0.55
    Activations Density 0.003%

    No Known Activations