© 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. 83828
    Prev
    Next
    INDEX
    Explanations

    offering alternatives or suggestions

    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
    frag
    0.47
    োগ
    0.46
     የታ
    0.46
    řed
    0.45
     죄
    0.45
    𝐞
    0.43
     اﻷ
    0.43
    anych
    0.41
     छापे
    0.41
     první
    0.41
    POSITIVE LOGITS
    But
    0.46
    2
    0.46
    ര്‍ന്ന്
    0.45
    ますが
    0.45
    Yesterday
    0.44
     rumours
    0.44
     taps
    0.43
    除了
    0.43
    することで
    0.43
     but
    0.43
    Activations Density 0.009%

    No Known Activations