© 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. 64120
    Prev
    Next
    INDEX
    Explanations

    target audience or purpose

    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
    t
    0.57
    pped
    0.53
    letta
    0.47
    posición
    0.46
    ge
    0.44
    entos
    0.44
    ótica
    0.41
    theta
    0.41
    unkt
    0.40
    gew
    0.40
    POSITIVE LOGITS
     aligns
    0.48
     utensil
    0.47
    氿
    0.47
     fridge
    0.46
     commandments
    0.45
     Saclay
    0.45
     Alignment
    0.45
    ریٹر
    0.45
     ascetic
    0.45
     dictionary
    0.44
    Activations Density 0.010%

    No Known Activations