© 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. 247
    Prev
    Next
    INDEX
    Explanations

    M words followed by specifics

    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
    বঙ্গে
    0.37
     어느
    0.37
    ías
    0.36
    Denied
    0.35
    ꯕ
    0.35
     вести
    0.35
    áreas
    0.34
     заме
    0.34
    relsen
    0.33
    Sexo
    0.33
    POSITIVE LOGITS
     M
    0.59
     MND
    0.57
     MH
    0.55
     mayhem
    0.54
     MT
    0.54
     Madness
    0.52
     MS
    0.51
     MN
    0.51
     എം
    0.50
     MW
    0.50
    Activations Density 0.502%

    No Known Activations