© 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
    2. Gemma-3-27B
    3. 53-GEMMASCOPE-2-RES-65K
    4. 17902
    Prev
    Next
    INDEX
    Explanations

    article identification and purpose

    np_acts-logits-general · gemini-2.5-flash-lite

    image and keywords sections

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_53_width_65k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     सोते
    0.44
    ってた
    0.43
    also
    0.43
    Oy
    0.43
    nione
    0.42
    adds
    0.41
    }$}
    0.40
    }}_{
    0.40
    }(-
    0.40
    replaced
    0.40
    POSITIVE LOGITS
     là
    0.49
    Cet
    0.47
     pust
    0.44
     entrou
    0.42
     hoist
    0.41
    خط
    0.39
     är
    0.39
     automaty
    0.38
     coding
    0.38
     Coding
    0.38
    Activations Density 0.000%

    No Known Activations