© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B-IT
    5. 31-GEMMASCOPE-2-RES-65K
    7. 8290
    Prev
    Next
    INDEX
    Explanations

    for followed by purpose

    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_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
     ৫
    0.52
     fünf
    0.52
    )
    0.49
     cinq
    0.47
    '
    0.46
    ห
    0.46
    Instruments
    0.46
    మ
    0.45
    </
    0.45
     eight
    0.44
    POSITIVE LOGITS
     ప్రజ
    0.51
    projekt
    0.47
    ermanfaat
    0.46
     shimmer
    0.45
    வதற்காக
    0.45
    生ま
    0.44
     좋아요
    0.44
     दीजिएगा
    0.43
     卡
    0.43
    ക്കാരി
    0.43
    Activations Density 0.007%

    No Known Activations