© 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. 19688
    Prev
    Next
    INDEX
    Explanations

    pressure, nudity, freezing, Greenland

    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
    ע
    0.43
    א
    0.40
    8
    0.37
    ה
    0.37
    Д
    0.36
    В
    0.35
    ва
    0.35
    리
    0.35
    су
    0.34
    не
    0.34
    POSITIVE LOGITS
     dirige
    0.33
     pengendalian
    0.32
     escenarios
    0.31
     eventi
    0.31
     biodivers
    0.31
     estratégico
    0.31
     skapa
    0.30
     décider
    0.30
     strategia
    0.30
     persiste
    0.29
    Activations Density 0.472%

    No Known Activations