© 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. 4203
    Prev
    Next
    INDEX
    Explanations

    adjectives suggesting significant qualities

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

    technical code and 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
    /
    0.37
    ikes
    0.36
     says
    0.35
    ↵
    0.33
    о
    0.33
    ers
    0.33
    says
    0.33
     auswählen
    0.32
     .
    0.32
     using
    0.32
    POSITIVE LOGITS
     undeniably
    0.48
     emblematic
    0.45
     wundersch
    0.43
     একটি
    0.42
     profoundly
    0.42
     brilliantly
    0.42
     unparalleled
    0.42
     undeniable
    0.42
     complejidad
    0.41
     prachtige
    0.41
    Activations Density 0.000%

    No Known Activations