© 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. 209705
    Prev
    Next
    INDEX
    Explanations

    arrest, killed, anymore

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

    what are curves

    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
     Gour
    0.52
    ু
    0.49
    數
    0.48
    劇場
    0.45
     –
    0.45
     Timberwolves
    0.44
    勵
    0.44
    ut
    0.44
    mán
    0.43
    剷
    0.43
    POSITIVE LOGITS
    crossing
    0.51
     mempelajari
    0.51
     فری
    0.50
    ificare
    0.49
    have
    0.47
    exactly
    0.47
    face
    0.46
    ressing
    0.46
     equivariant
    0.45
     resor
    0.44
    Activations Density 0.000%

    No Known Activations