© 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. 188106
    Prev
    Next
    INDEX
    Explanations

    vehicle cost exceeds value

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

    tasks or absorption

    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
     curiously
    0.49
     extracellular
    0.49
     ikon
    0.47
    異
    0.47
     في
    0.46
     circa
    0.46
     عام
    0.46
     supra
    0.46
     peek
    0.46
     heterod
    0.45
    POSITIVE LOGITS
    绺
    0.50
    īga
    0.48
    ệu
    0.46
    ố
    0.46
     coûts
    0.45
    alarının
    0.45
    ič
    0.45
    然后
    0.44
    ग्गा
    0.44
    órmula
    0.44
    Activations Density 0.001%

    No Known Activations