© 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-2-27B
    5. 22-GEMMASCOPE-RES-131K
    7. 13901
    Prev
    Next
    INDEX
    Explanations

    hashing algorithms sha1 md5 rsa

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

    This neuron detects version numbers in cryptographic hash algorithm names (e.g. the “1” in SHA1, the “5” in MD5, the “256” in SHA256).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_22/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
    に戻る
    -1.66
    事で
    -1.47
    感じで
    -1.46
     Therefore
    -1.41
     Also
    -1.38
     and
    -1.36
    に戻
    -1.34
    際に
    -1.33
     However
    -1.30
    感じです
    -1.28
    POSITIVE LOGITS
     of
    1.74
    ですが
    1.57
    と
    1.49
    で
    1.47
    に
    1.45
    があります
    1.45
    そして
    1.41
    もある
    1.41
    だが
    1.40
    は
    1.40
    Activations Density 0.001%

    No Known Activations