© 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. 18775
    Prev
    Next
    INDEX
    Explanations

    the more the more

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

    the more, the more

    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
     unterstüt
    0.43
     อาจ
    0.43
    _:
    0.42
    Sek
    0.42
    比如說
    0.41
     potrebbe
    0.39
     אחר
    0.39
     έναν
    0.39
    䂧
    0.38
    鬘
    0.38
    POSITIVE LOGITS
    越多
    1.05
    越大
    0.91
    越高
    0.91
     desto
    0.87
     càng
    0.86
    수록
    0.86
    ยิ่ง
    0.80
     ততই
    0.76
    越
    0.72
     जितना
    0.72
    Activations Density 0.067%

    No Known Activations