© 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. 49126
    Prev
    Next
    INDEX
    Explanations

    family or business contexts

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

    Chorus in lyrics

    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
    glu
    0.51
    글
    0.49
    st
    0.47
    producto
    0.47
    g
    0.46
    gl
    0.46
    ⵣ
    0.44
    use
    0.44
    la
    0.43
    urgical
    0.43
    POSITIVE LOGITS
     dukkham
    0.50
     رم
    0.49
     единица
    0.49
     يجعل
    0.49
     пят
    0.46
    اني
    0.45
     أبي
    0.45
     muškar
    0.45
    ابي
    0.44
    𝕟
    0.43
    Activations Density 0.000%

    No Known Activations