© 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. 81352
    Prev
    Next
    INDEX
    Explanations

    investment, international, sophisticated

    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
    疱
    0.41
    :
    0.41
    ிழமை
    0.41
     बजकर
    0.40
     baños
    0.40
    甩
    0.40
     بیم
    0.39
     اشک
    0.39
    ك
    0.39
    利亚
    0.39
    POSITIVE LOGITS
    ವೇಂದ್ರ
    0.49
     entrepreneurial
    0.44
    u
    0.43
     internationally
    0.42
     internazionale
    0.42
     newer
    0.42
    우스
    0.41
     новой
    0.41
     jeweler
    0.41
    वेश
    0.41
    Activations Density 0.009%

    No Known Activations