© 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. 11808
    Prev
    Next
    INDEX
    Explanations

    saw what was

    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
     those
    -1.27
    ですが
    -1.20
    though
    -1.16
    тно
    -1.12
    、
    -1.11
    </u>
    -1.10
    彼女は
    -1.08
    xe
    -1.06
    днако
    -1.06
     some
    -1.05
    POSITIVE LOGITS
    の可能性
    1.41
    癀
    1.25
     poderia
    1.25
    慊
    1.20
     dónde
    1.18
    thical
    1.16
    才知道
    1.14
    でいい
    1.13
    デザ
    1.13
    えもん
    1.12
    Activations Density 0.048%

    No Known Activations