© 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. 22-GEMMASCOPE-RES-131K
    7. 14261
    Prev
    Next
    INDEX
    Explanations

    DBA, Timothy, disgruntled

    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_22/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
    ловая
    -1.23
    総評
    -1.23
    のではない
    -1.23
     علاوه
    -1.21
    気がする
    -1.16
     manquante
    -1.16
     These
    -1.16
    ⣉
    -1.16
     Already
    -1.13
     chrétienne
    -1.12
    POSITIVE LOGITS
    ↵
    1.56
    なども
    1.17
    brtc
    1.13
     how
    1.08
    それが
    1.08
    などが
    1.03
    車が
    1.03
    gmail
    1.02
    $\
    1.02
    need
    1.00
    Activations Density 0.016%

    No Known Activations