© 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. 169601
    Prev
    Next
    INDEX
    Explanations

    power, limited, outperform, licensed, providing

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

    LIAM or LIP

    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
     Expenditure
    0.51
     produ
    0.47
     Characteristics
    0.46
    撾
    0.46
     Fairview
    0.46
    icuously
    0.45
     abnormal
    0.45
     Maximum
    0.45
     Abnormal
    0.45
     দিয়েছেন
    0.45
    POSITIVE LOGITS
    อิน
    0.57
     मूव
    0.45
    ZA
    0.44
    Ո
    0.44
    คลิ
    0.44
    Ң
    0.44
    ถูก
    0.43
    did
    0.43
    HIP
    0.42
     disamb
    0.42
    Activations Density 0.000%

    No Known Activations