© 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. 42166
    Prev
    Next
    INDEX
    Explanations

    gain and acquisition

    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
    が違う
    -1.17
     realizando
    -1.14
     –
    -1.13
    ?”
    -1.10
     zasady
    -1.09
     versions
    -1.08
    a
    -1.07
    噘
    -1.05
     Parteien
    -1.05
     —
    -1.03
    POSITIVE LOGITS
    ők
    1.27
    вня
    1.21
     grabar
    1.20
     Masalah
    1.20
     veci
    1.17
     tady
    1.16
     telas
    1.15
    staun
    1.15
    восто
    1.14
     Meningkatkan
    1.14
    Activations Density 0.105%

    No Known Activations