© 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. 156134
    Prev
    Next
    INDEX
    Explanations

    East, except, policies, red, hard

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

    resource assessment, fluids, route optimization

    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
     மொழி
    0.49
     machine
    0.49
     syllables
    0.46
     imprisonment
    0.45
     தொடங்கிய
    0.45
    weapp
    0.45
    speech
    0.44
    እ
    0.44
     shells
    0.43
     keyboards
    0.43
    POSITIVE LOGITS
    焚
    0.46
    ampi
    0.45
    하고자
    0.45
     thiab
    0.44
     spør
    0.43
    ijiet
    0.43
    iret
    0.42
    考虑
    0.42
     desiderio
    0.42
     regenerated
    0.42
    Activations Density 0.001%

    No Known Activations