© 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-IT
    5. 40-GEMMASCOPE-2-RES-262K
    7. 35867
    Prev
    Next
    INDEX
    Explanations

    Okay, let's start

    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_40_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
    string
    0.49
     string
    0.46
     preferably
    0.45
    릎
    0.44
     moreover
    0.43
     otherwise
    0.43
     combined
    0.42
    ling
    0.42
    (_.
    0.42
     purposely
    0.42
    POSITIVE LOGITS
     başlayalım
    0.43
     অবশেষে
    0.42
     veamos
    0.42
    Firstly
    0.42
     Firstly
    0.41
     hablaremos
    0.41
     본격
    0.41
     rumores
    0.40
     이제
    0.40
    Finally
    0.39
    Activations Density 0.022%

    No Known Activations