© 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. 105956
    Prev
    Next
    INDEX
    Explanations

    -----BEGIN RSA PRIVATE KEY-----

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

    The neuron is detecting hexadecimal byte values (sequences of hex digits, e.g. “0A,” “CA,” long hex strings).

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    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
     was
    -1.47
    );
    -1.41
     تصریح
    -1.40
    ]
    -1.37
     suficientes
    -1.37
    ană
    -1.36
     estrictamente
    -1.34
     benutzen
    -1.34
     exclusivamente
    -1.33
     numerosos
    -1.33
    POSITIVE LOGITS
    淠
    1.71
    嫆
    1.59
    .
    1.59
     ANCHE
    1.58
    Ça
    1.54
    はこんな感じ
    1.53
     cubana
    1.52
     parten
    1.51
     TAMBIÉN
    1.46
    tains
    1.44
    Activations Density 0.002%

    No Known Activations