© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Gemma-2-27B
    3. 22-GEMMASCOPE-RES-131K
    4. 12164
    Prev
    Next
    INDEX
    Explanations

    introductions and labels

    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
     other
    -1.39
    本科
    -1.14
     سایر
    -1.12
    顶级
    -1.10
     difficult
    -1.09
    Other
    -1.06
     their
    -1.06
    euros
    -1.03
     similar
    -1.02
    бари
    -1.02
    POSITIVE LOGITS
     však
    1.23
    ilions
    1.22
    を
    1.19
     svůj
    1.16
    などが
    1.16
     ſee
    1.15
     víc
    1.15
    もありますが
    1.13
    もあって
    1.13
    などを
    1.13
    Activations Density 0.000%

    No Known Activations