© 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. 40-GEMMASCOPE-2-RES-16K
    7. 10012
    Prev
    Next
    INDEX
    Explanations

    introducing a topic or action

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

    checking status or conditions

    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_40_width_16k_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
    Keep
    0.43
    EDIT
    0.41
    Hmm
    0.40
    Arts
    0.40
    ぬ
    0.40
    OVE
    0.38
    ActionEvent
    0.37
    elev
    0.37
    Outcome
    0.37
    SS
    0.36
    POSITIVE LOGITS
     பயிற்சிய
    0.47
    🍋
    0.43
     கால
    0.42
     प्रशिक्
    0.42
     Chub
    0.42
     প্রশিক্ষ
    0.41
     trainee
    0.41
     Parser
    0.41
     blocks
    0.39
    ulkner
    0.38
    Activations Density 0.023%

    No Known Activations