© 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-3-270M-IT
    5. 12-GEMMASCOPE-2-RES-65K
    7. 2139
    Prev
    Next
    INDEX
    Explanations

    performance improvement, audience, incredible descriptions

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-270m-it/resid_post/layer_12_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
     Vortex
    1.35
     ICA
    1.31
    IFS
    1.27
     Bibi
    1.27
     Robbins
    1.26
    薏
    1.25
     Bingo
    1.23
    ivr
    1.20
     Bree
    1.19
     compass
    1.18
    POSITIVE LOGITS
    </
    0.85
    μένου
    0.65
    гне
    0.62
    滁
    0.59
    Jul
    0.58
    нях
    0.51
    绅
    0.50
    gh
    0.49
    Done
    0.48
    Kum
    0.48
    Activations Density 0.110%

    No Known Activations