© 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. 13134
    Prev
    Next
    INDEX
    Explanations

    doing it yourself

    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
     और
    0.58
     и
    0.54
     và
    0.50
     και
    0.50
     અને
    0.50
     आणि
    0.47
     এবং
    0.46
    정과
    0.44
     ו
    0.43
    υτό
    0.43
    POSITIVE LOGITS
    Bak
    0.46
    Website
    0.45
    Man
    0.44
    Harm
    0.44
    ⴼ
    0.44
    Queen
    0.43
    Independent
    0.42
    Web
    0.42
    Princess
    0.41
    Til
    0.41
    Activations Density 0.007%

    No Known Activations