© 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. 38095
    Prev
    Next
    INDEX
    Explanations

    confirm and confirmation

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

    confirming actions or information

    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
     insolvent
    0.54
    一丝
    0.53
    IF
    0.52
    ാല
    0.51
    kul
    0.51
    l
    0.51
    }
    0.51
     Adhesive
    0.50
    v
    0.50
    stan
    0.50
    POSITIVE LOGITS
    确认
    1.34
     confirm
    1.31
     confirming
    1.27
     confirmations
    1.27
    confirm
    1.24
    確認
    1.20
     confirms
    1.20
     Confirm
    1.20
    confirmation
    1.19
    confirmed
    1.17
    Activations Density 0.055%

    No Known Activations