© 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. 92881
    Prev
    Next
    INDEX
    Explanations

    descriptions of actions and their consequences

    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
    竰
    0.43
     inflexible
    0.41
     TComponent
    0.40
     entitled
    0.40
    𒋼
    0.39
    保管
    0.39
    θηκε
    0.39
     Seriously
    0.39
    <unused2064>
    0.39
     hemicontinuous
    0.38
    POSITIVE LOGITS
    AddTo
    0.47
     charlas
    0.47
     invasions
    0.45
     concerts
    0.44
     retaliation
    0.44
    day
    0.43
     agosto
    0.43
    вый
    0.42
    ResultMessage
    0.41
     académica
    0.41
    Activations Density 0.007%

    No Known Activations