© 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. 34-GEMMASCOPE-RES-131K
    7. 83944
    Prev
    Next
    INDEX
    Explanations

    message separators

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

    The neuron is chiefly triggered by numeric tokens and long digit‐ or punctuation‐only sequences (e.g. stand‐alone numbers, dates, line-of-hyphens, large numeric codes).

    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
    xxxxxxxxxxxxxxxx
    -0.74
     }(\
    -0.72
    };
    -0.71
    . 
    -0.70
    ignées
    -0.70
    
    -0.70
     ».
    -0.70
    ">+
    -0.69
    Formulario
    -0.68
    . 
    -0.68
    POSITIVE LOGITS
    ---
    3.28
     ---
    3.11
    -----
    2.45
     ----
    2.39
     -----
    2.36
    ----
    2.33
    ------
    2.17
    ___
    2.11
     "---
    2.05
    ---
    2.00
    Activations Density 0.233%

    No Known Activations