© 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. 99464
    Prev
    Next
    INDEX
    Explanations

    appearance and style descriptors

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

    superlative adjectives and specific states

    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
    ᒎ
    0.46
     もう
    0.44
    ці
    0.44
     integrable
    0.43
    ERCISE
    0.41
    ถ
    0.41
    ('/',
    0.40
    ⵉ
    0.39
     ঢেউ
    0.39
     よく
    0.38
    POSITIVE LOGITS
    专注于
    0.48
    irah
    0.47
    ,​
    0.41
    ခံ
    0.40
    夷
    0.40
    𝐍
    0.40
    انو
    0.39
     cultured
    0.39
     Mana
    0.39
     বিনা
    0.39
    Activations Density 0.001%

    No Known Activations