© 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-262K
    7. 110815
    Prev
    Next
    INDEX
    Explanations

    multiple languages or scripts

    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
     abgesch
    0.47
     s
    0.46
     Sts
    0.44
     ang
    0.44
     uts
    0.44
     abhiv
    0.43
    getMessage
    0.42
     ts
    0.41
     Response
    0.41
     ii
    0.41
    POSITIVE LOGITS
    И
    0.56
    𝗕
    0.55
    Dans
    0.54
    Enfin
    0.54
    Ин
    0.54
    Нет
    0.53
    Crim
    0.53
    Ис
    0.53
    Neces
    0.52
    Ве
    0.52
    Activations Density 0.000%

    No Known Activations