© 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. 8130
    Prev
    Next
    INDEX
    Explanations

    understanding how things work

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

    understand

    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
     নিলাম
    0.39
    })$.
    0.35
     anunciou
    0.35
     }^{+}$
    0.34
     ইমর
    0.34
     นิ
    0.34
     જોવા
    0.34
     आसन
    0.33
     उत
    0.33
    }$.
    0.33
    POSITIVE LOGITS
     understands
    0.55
     recognises
    0.55
     reconnaître
    0.53
     recognise
    0.52
     recognising
    0.50
     aware
    0.50
     dangers
    0.48
     recognizes
    0.48
     recognised
    0.48
     acknowledges
    0.48
    Activations Density 0.261%

    No Known Activations