© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 5472
    Prev
    Next
    INDEX
    Explanations

    mentioning dates and references

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

    numbers and evaluation

    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_31_width_262k_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
    स्तिष्क
    0.39
    ána
    0.37
    नीचर
    0.37
    atthena
    0.36
    퐶
    0.36
    बारक
    0.35
     loài
    0.35
    𒀝
    0.35
    사람
    0.35
    माटर
    0.34
    POSITIVE LOGITS
    0.47
     mentioned
    0.46
     aforementioned
    0.46
     &
    0.41
     mencionado
    0.39
    mentioned
    0.37
     aforesaid
    0.36
    ↵
    0.35
     \
    0.35
     mencionados
    0.35
    Activations Density 0.127%

    No Known Activations