© 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. 190206
    Prev
    Next
    INDEX
    Explanations

    foreign language or specific terms

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

    way humans can

    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
     Illuminate
    0.48
     Hopefully
    0.46
    ージャー
    0.46
     galima
    0.45
    ᄌ
    0.43
    獼
    0.42
    .—
    0.41
    возможно
    0.40
    ADDING
    0.40
    OBER
    0.40
    POSITIVE LOGITS
    lia
    0.53
    rul
    0.47
    uine
    0.45
    mati
    0.44
    oli
    0.42
    lil
    0.42
    すす
    0.41
    dun
    0.41
    协商
    0.41
    熵
    0.41
    Activations Density 0.000%

    No Known Activations