© 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. 168694
    Prev
    Next
    INDEX
    Explanations

    public/private partnership

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

    redirect or kidnapped

    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
     paternity
    0.53
    ii
    0.49
    volution
    0.47
    un
    0.46
    pute
    0.45
    vi
    0.45
    }^{-}\
    0.44
    ag
    0.44
    putes
    0.43
    த்தூர்
    0.42
    POSITIVE LOGITS
     весь
    0.52
     cuyo
    0.49
    着
    0.49
    preventDefault
    0.48
     час
    0.47
     это
    0.47
    果然
    0.47
     начинается
    0.47
    метка
    0.47
    щего
    0.47
    Activations Density 0.001%

    No Known Activations