© 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. 98161
    Prev
    Next
    INDEX
    Explanations

    how we might

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

    break down explanation

    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
    :
    0.46
     plasmids
    0.43
     CRISPR
    0.41
     tracers
    0.41
     fertilizers
    0.41
     protein
    0.40
     adhesives
    0.39
     SDGs
    0.39
     heres
    0.39
     lungs
    0.38
    POSITIVE LOGITS
    ப்பர்
    0.44
    ండే
    0.44
    Converting
    0.43
     уен
    0.42
    ⵡ
    0.42
     டாக்டர்
    0.42
    ᚨ
    0.42
    ༞
    0.42
    ồi
    0.41
     リボン
    0.41
    Activations Density 0.000%

    No Known Activations