© 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. 22-GEMMASCOPE-RES-131K
    7. 36195
    Prev
    Next
    INDEX
    Explanations

    following guidelines and regulations

    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
     ErrInvalid
    -1.08
    สำหรับ
    -1.05
     for
    -0.98
     össze
    -0.93
     after
    -0.88
    ENCIL
    -0.88
    病例
    -0.87
    После
    -0.86
     для
    -0.85
    ᴺ
    -0.85
    POSITIVE LOGITS
     geprek
    1.22
     behaviour
    1.07
    かれている
    1.00
     将
    0.97
     compliance
    0.97
     Θ
    0.95
    umplimiento
    0.94
    ⅼ
    0.94
     PERSON
    0.94
    ⅓
    0.93
    Activations Density 0.039%

    No Known Activations