© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-262K
    7. 28873
    Prev
    Next
    INDEX
    Explanations

    monetary values ($)

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Афри
    0.40
     стоимо
    0.39
     እንዲሁም
    0.39
     pence
    0.39
    ництва
    0.39
     ενώ
    0.38
     transg
    0.38
    💂
    0.38
    螺
    0.38
    дал
    0.37
    POSITIVE LOGITS
     is
    0.50
     Camera
    0.46
    ated
    0.44
    Decrease
    0.43
     Sight
    0.41
     decrease
    0.41
     Feature
    0.40
     Font
    0.39
     Game
    0.39
    unteers
    0.39
    Activations Density 0.008%

    No Known Activations