© 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-262K
    7. 75549
    Prev
    Next
    INDEX
    Explanations

    pickup lines and explanations

    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_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
    囁
    0.42
    然後
    0.42
     ازيكم
    0.42
    犃
    0.42
     يكون
    0.41
     neoplasms
    0.41
     Rồi
    0.41
    ภ
    0.41
     affirmations
    0.40
     تكون
    0.40
    POSITIVE LOGITS
    从小
    0.51
     delegated
    0.43
     increased
    0.43
     oportunidad
    0.42
     delegation
    0.42
     backlash
    0.42
    ዉ
    0.41
     brou
    0.41
     downed
    0.41
     delegations
    0.40
    Activations Density 0.011%

    No Known Activations