© 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. 104668
    Prev
    Next
    INDEX
    Explanations

    slap him

    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
     réfrig
    -1.45
     cucharadita
    -1.41
    めます
    -1.27
     сосе
    -1.17
    см
    -1.17
     cucharada
    -1.16
    aménagement
    -1.09
    瞠
    -1.09
     знамени
    -1.08
    </em>
    -1.07
    POSITIVE LOGITS
    ṝ
    1.46
    ɵɵelement
    1.38
    本日は
    1.19
    jaket
    1.18
    ᚨ
    1.16
    本日の
    1.15
     ativar
    1.14
    Glej
    1.13
     farà
    1.13
    原始内容
    1.13
    Activations Density 0.003%

    No Known Activations