© 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-65K
    7. 10805
    Prev
    Next
    INDEX
    Explanations

    words followed by specific contexts

    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_65k_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
     questi
    0.45
    </
    0.45
     regioni
    0.44
     mondo
    0.42
     regiones
    0.42
     metade
    0.42
     hoja
    0.40
     capas
    0.40
     جبکہ
    0.40
    rightarrow
    0.39
    POSITIVE LOGITS
     VICTOR
    0.42
    疖
    0.42
    蟳
    0.41
    デジタル
    0.40
     разнообраз
    0.40
    蕤
    0.40
    天然
    0.39
    ꔰ
    0.39
    Formal
    0.39
    সং
    0.38
    Activations Density 0.004%

    No Known Activations