© 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. 194878
    Prev
    Next
    INDEX
    Explanations

    specialized contexts and subsequent actions

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

    based on concepts

    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
    irne
    0.52
    esehen
    0.50
    જા
    0.47
    upe
    0.47
    increment
    0.47
    aine
    0.47
     имена
    0.47
    }+\
    0.46
    elapsed
    0.46
     នៅ
    0.46
    POSITIVE LOGITS
     candles
    0.49
     mendatang
    0.47
     pem
    0.45
     JESUS
    0.45
     dilapidated
    0.45
     dedans
    0.44
     backpack
    0.44
     dioc
    0.44
     whisper
    0.44
     million
    0.43
    Activations Density 0.002%

    No Known Activations