© 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. 74623
    Prev
    Next
    INDEX
    Explanations

    Rashid, Rashford, Lash, Raschig, Raspbian

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

    The neuron strongly activates on tokens containing the character sequence “rash” (as in Rashid, Marcus Rashford, Raschig, Rashmi, Lashkar).

    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
    ]
    -2.50
     正面
    -2.45
     服装
    -2.36
    𝄆
    -2.30
     It
    -2.30
    大半
    -2.17
    ázaro
    -2.16
     Again
    -2.13
     Then
    -2.08
     标志
    -2.02
    POSITIVE LOGITS
    ’
    4.53
    ه
    3.27
    “
    2.98
    2
    2.75
    to
    2.69
    i
    2.66
     lakini
    2.39
    ꪔ
    2.33
    the
    2.33
    ine
    2.31
    Activations Density 0.001%

    No Known Activations