© 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. 13143
    Prev
    Next
    INDEX
    Explanations

    names followed by states of being

    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
    ,
    0.54
     of
    0.47
     अनेक
    0.44
    ),
    0.43
     многих
    0.42
    }$,
    0.42
     muchas
    0.41
    或其他
    0.41
     различных
    0.40
     various
    0.40
    POSITIVE LOGITS
     visualiser
    0.42
    បញ្ចប់
    0.42
    𒉺
    0.42
    𒌋
    0.41
    Encript
    0.41
    🖕
    0.40
    三天
    0.40
     trois
    0.39
     raping
    0.39
     ત્રણ
    0.39
    Activations Density 0.036%

    No Known Activations