© 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. 14141
    Prev
    Next
    INDEX
    Explanations

    saving money and expenses

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

    being clear and readable

    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
    仅
    0.44
     Offered
    0.43
     обновления
    0.43
    inha
    0.42
    因
    0.42
    Pon
    0.41
    ян
    0.41
    ⠀
    0.41
     поста
    0.41
    गान
    0.40
    POSITIVE LOGITS
     utiliz
    0.41
     translocation
    0.40
     manipulation
    0.39
     scavenging
    0.39
     vess
    0.39
     tradicion
    0.39
    Substituting
    0.39
     specif
    0.38
     hawk
    0.37
     inactiv
    0.37
    Activations Density 0.001%

    No Known Activations