© 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. 5428
    Prev
    Next
    INDEX
    Explanations

    declaration of commitment

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

    commitment to something

    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
    designer
    0.52
     নজর
    0.49
    𝒚
    0.48
    咨
    0.47
    ives
    0.47
    quillo
    0.46
    ı
    0.46
    ług
    0.46
     Muller
    0.46
    <0x9B>
    0.46
    POSITIVE LOGITS
     commitment
    1.11
     commitments
    1.09
     Commit
    1.08
     commit
    1.02
     committing
    0.99
     committed
    0.93
    Commit
    0.93
    承诺
    0.93
     COMMIT
    0.91
     Commitment
    0.91
    Activations Density 0.051%

    No Known Activations