© 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. 96697
    Prev
    Next
    INDEX
    Explanations

    public, memorial, created, answer

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

    sensory or conceptual understanding

    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
    鱉
    0.48
     outings
    0.45
     tracts
    0.44
     currentRow
    0.44
    𝗸
    0.43
     presided
    0.42
    hile
    0.42
     disbursements
    0.42
     मालम
    0.41
     PASSWORD
    0.41
    POSITIVE LOGITS
    掩
    0.46
    Quantitative
    0.44
     verdadeira
    0.44
    quantitative
    0.44
     yüks
    0.42
    elevation
    0.42
    ğine
    0.42
    بت
    0.41
    いだ
    0.41
    یت
    0.40
    Activations Density 0.001%

    No Known Activations