© 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. 64104
    Prev
    Next
    INDEX
    Explanations

    aliased columns `AS`

    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
    a
    0.50
     denounced
    0.48
     enraged
    0.48
     disobedience
    0.47
     horrors
    0.47
     excruciating
    0.47
     horrific
    0.46
     apocalyptic
    0.46
    https
    0.46
     g
    0.45
    POSITIVE LOGITS
     металли
    0.51
    ፩
    0.48
    Ѡ
    0.47
    반
    0.47
    OUGHT
    0.47
    మీ
    0.46
    ቒ
    0.46
    িতা
    0.45
    ᆸ
    0.45
    Contacto
    0.44
    Activations Density 0.020%

    No Known Activations