© 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-2-27B
    5. 10-GEMMASCOPE-RES-131K
    7. 68223
    Prev
    Next
    INDEX
    Explanations

    Ptr or Robbie name

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

    The neuron specifically activates on occurrences of the code identifier “Ptr” (e.g. in type or pointer definitions).

    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
    0
    -3.88
    6
    -3.23
    7
    -3.13
    9
    -3.02
    4
    -2.95
    3
    -2.80
    8
    -2.69
    5
    -2.64
    1
    -2.64
     {
    -2.39
    POSITIVE LOGITS
    鸸
    2.34
    '
    2.34
    ),
    2.27
     lopez
    2.22
    逦
    2.20
    鲼
    2.20
     pharmacie
    2.19
     pantal
    2.19
    窗户
    2.17
    踯
    2.17
    Activations Density 0.001%

    No Known Activations