© 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-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 15254
    Prev
    Next
    INDEX
    Explanations

    future actions and purposes

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-it/resid_post/layer_31_width_65k_l0_medium
    Prompts (Dashboard)
    238,145 prompts, 512 tokens each
    Dataset (Dashboard)
    lmsys + oasst1
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     seeming
    0.59
     seemed
    0.51
    
    0.50
    🫤
    0.50
    似乎
    0.49
     való
    0.47
    🫣
    0.46
     อืม
    0.46
    ლებიც
    0.46
     പോലും
    0.45
    POSITIVE LOGITS
     tomorrow
    0.49
     future
    0.47
    ’
    0.46
     D
    0.46
    0.45
     will
    0.44
     on
    0.44
     미래
    0.44
     futuro
    0.43
    sthe
    0.43
    Activations Density 0.036%

    No Known Activations