© 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. 34-GEMMASCOPE-RES-131K
    7. 31744
    Prev
    Next
    INDEX
    Explanations

    Raymond, Ramb, Raman

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

    The neuron responds to occurrences of the letter sequence “ram” (as in “Rambouillet,” “Raman,” “Raymond,” etc.) within tokens.

    oai_token-act-pair · o4-miniTriggered by @jyhe0408
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-27b-pt-res/layer_34/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
     سخن
    -0.81
    𝗞
    -0.78
    -------
    -0.78
    OrFail
    -0.77
     romana
    -0.75
    🧟
    -0.73
    ᵊ
    -0.73
    ---
    -0.73
    ricul
    -0.72
    ონ
    -0.71
    POSITIVE LOGITS
    ł
    0.85
     доход
    0.77
     vstup
    0.76
     Hyp
    0.72
    pn
    0.70
    льність
    0.69
    Bij
    0.69
    FAC
    0.68
    Playback
    0.68
    USP
    0.68
    Activations Density 0.017%

    No Known Activations