© 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. 10-GEMMASCOPE-RES-131K
    7. 13113
    Prev
    Next
    INDEX
    Explanations

    salam and alam names

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

    The neuron strongly activates on tokens containing the substring “alam” (e.g. “Salam,” “Alamofire,” etc.).

    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
     "
    -3.02
     "'
    -2.95
     szczególnie
    -2.58
     "...
    -2.55
     その
    -2.53
     "[
    -2.44
    頂き
    -2.44
     deliciously
    -2.42
    について
    -2.42
     However
    -2.42
    POSITIVE LOGITS
     nader
    2.58
     )
    2.56
     ]
    2.55
    هما
    2.55
     關
    2.50
    肏
    2.45
    筚
    2.45
    ]
    2.42
     twor
    2.41
     itſelf
    2.41
    Activations Density 0.013%

    No Known Activations