© 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. 102602
    Prev
    Next
    INDEX
    Explanations

    real estate

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

    matters, care, leave, data, set

    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
    悪
    0.51
    ミル
    0.47
     vieux
    0.43
     Ford
    0.43
    और
    0.42
     folly
    0.42
     American
    0.41
     आव
    0.41
    下面
    0.41
    เพราะ
    0.41
    POSITIVE LOGITS
    ä
    0.53
    one
    0.49
    crt
    0.48
     अनन्या
    0.47
    ulter
    0.46
    ängt
    0.46
    ět
    0.45
    idades
    0.45
     包括
    0.45
    स्ड
    0.44
    Activations Density 0.000%

    No Known Activations