© 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. 10-GEMMASCOPE-RES-131K
    7. 70570
    Prev
    Next
    INDEX
    Explanations

    string formatting and joining

    np_acts-logits-general · gemini-2.5-flash-lite
    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
     and
    -2.44
    ⃑
    -1.91
     actitud
    -1.84
    銕
    -1.80
    撳
    -1.75
     legislación
    -1.65
     contribución
    -1.63
     celebrid
    -1.63
    οντας
    -1.59
    enschappe
    -1.58
    POSITIVE LOGITS
    3
    2.88
    4
    2.83
    '
    2.59
    ?
    2.58
    6
    2.53
    8
    2.52
    5
    2.47
    .
    2.41
    9
    2.38
    2
    2.33
    Activations Density 0.000%

    No Known Activations