© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 110997
    Prev
    Next
    INDEX
    Explanations

    ika, Laika, Zika, tika

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

    names or words that end with "ika" in various languages and contexts.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @neilrathi
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_10/width_131k
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    "
    -3.19
     we
    -2.67
    ,"
    -2.58
    al
    -2.50
     frantically
    -2.28
     they
    -2.23
    I
    -2.20
     is
    -2.16
    la
    -2.11
    镚
    -2.08
    POSITIVE LOGITS
    ika
    3.23
    IKA
    2.38
    こともあり
    2.30
    いかがでしたか
    2.27
    of
    2.27
    んだけど
    2.22
     británica
    2.22
     ساعد
    2.19
     opsi
    2.17
    难以
    2.14
    Activations Density 0.005%

    No Known Activations