© 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. 10-GEMMASCOPE-RES-131K
    7. 99523
    Prev
    Next
    INDEX
    Explanations

    potential future events

    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
    壜
    -2.86
    ſſen
    -2.78
    錞
    -2.64
    ᚔ
    -2.59
     この
    -2.59
    鯢
    -2.58
    蚍
    -2.55
    ꦢ
    -2.53
    冏
    -2.52
    毳
    -2.48
    POSITIVE LOGITS
     Actually
    3.47
     Basically
    3.36
     Also
    3.31
     Notably
    3.30
     Apparently
    3.19
     Importantly
    3.19
    -
    3.16
     Mostly
    3.09
     Usually
    3.08
    .
    3.08
    Activations Density 0.012%

    No Known Activations