© 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. 40-GEMMASCOPE-2-RES-262K
    7. 2085
    Prev
    Next
    INDEX
    Explanations

    used for and to

    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_40_width_262k_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
    being
    0.38
    বাসীর
    0.36
    취
    0.36
    viridis
    0.36
    发生
    0.35
    हिट
    0.35
    jobSize
    0.35
    hitting
    0.35
    丹
    0.35
     moelle
    0.35
    POSITIVE LOGITS
     interchangeably
    0.81
     sparingly
    0.72
     extensively
    0.70
     để
    0.64
     upang
    0.59
     для
    0.59
     for
    0.57
     conjunction
    0.55
    ในการ
    0.52
     to
    0.49
    Activations Density 0.036%

    No Known Activations