© 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-65K
    7. 55844
    Prev
    Next
    INDEX
    Explanations

    longest streak

    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_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
     Sema
    0.38
    тні
    0.38
     appraisals
    0.38
    鍘
    0.38
     புற
    0.37
    порта
    0.36
     computational
    0.36
     Computational
    0.36
     살
    0.36
    Mord
    0.36
    POSITIVE LOGITS
     streak
    1.59
     streaks
    1.34
    streak
    1.29
     Streak
    1.28
    Streak
    1.23
     longest
    1.05
    longest
    0.94
     unbroken
    0.90
     series
    0.86
     séries
    0.82
    Activations Density 0.055%

    No Known Activations