© 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
    2. Gemma-2-27B
    3. 10-GEMMASCOPE-RES-131K
    4. 87094
    Prev
    Next
    INDEX
    Explanations

    introduces topic

    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
    lindung
    -1.30
    鳢
    -1.25
    ⁺
    -1.24
    loginButton
    -1.20
    lebih
    -1.18
    "।
    -1.16
    淒
    -1.13
    锱
    -1.13
    喟
    -1.13
     itſelf
    -1.10
    POSITIVE LOGITS
    windig
    1.31
    imanapun
    1.30
    /
    1.24
     נוסף
    1.23
    type
    1.21
    更大
    1.19
     myriad
    1.19
    Ώ
    1.16
     jedną
    1.13
    rdquo
    1.12
    Activations Density 0.061%

    No Known Activations