© 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-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 56853
    Prev
    Next
    INDEX
    Explanations

    responsible for actions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Phas
    0.50
    }$.
    0.47
    ziła
    0.46
     Kes
    0.44
    ∙
    0.44
     اکثر
    0.42
    Zi
    0.42
    ửa
    0.42
    }$
    0.41
     Felix
    0.40
    POSITIVE LOGITS
     primeiras
    0.58
     necessárias
    0.55
     primeras
    0.55
     désormais
    0.55
     investigación
    0.51
     etiqueta
    0.50
     kroner
    0.50
     páginas
    0.49
     inicialmente
    0.48
     chave
    0.47
    Activations Density 0.001%

    No Known Activations