© 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. 142273
    Prev
    Next
    INDEX
    Explanations

    distance between

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

    objects and places

    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
    ের
    0.49
    zać
    0.47
     emphatic
    0.47
    壘
    0.44
     takiego
    0.43
    }\
    0.43
    ிகா
    0.42
    iega
    0.42
     infrequent
    0.41
    retien
    0.41
    POSITIVE LOGITS
     سپس
    0.55
     ядра
    0.54
     ре
    0.53
     mình
    0.52
     базы
    0.52
     հ
    0.48
     وحدة
    0.47
     کہاں
    0.47
     مہ
    0.47
     projet
    0.47
    Activations Density 0.004%

    No Known Activations