© 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. 40-GEMMASCOPE-2-RES-65K
    7. 1202
    Prev
    Next
    INDEX
    Explanations

    context and audience

    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_40_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
     arba
    0.44
     følgende
    0.43
     vara
    0.42
    }$\\
    0.42
     sparingly
    0.42
     flamb
    0.40
    )$\\
    0.40
     vard
    0.38
     yoki
    0.38
     temporal
    0.37
    POSITIVE LOGITS
    д
    0.58
    总之
    0.53
    an
    0.50
    I
    0.47
    z
    0.46
    这样
    0.46
    helps
    0.44
    basically
    0.44
     Ultimately
    0.44
    halten
    0.44
    Activations Density 0.111%

    No Known Activations