© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Gemma-3-27B
    5. 31-GEMMASCOPE-2-RES-262K
    7. 197642
    Prev
    Next
    INDEX
    Explanations

    technical citation details

    np_acts-logits-general · gemini-2.5-flash-lite

    Time compression, unsigned integer, huge expansion, cost benefits, moral benefits

    np_acts-logits-general · gemini-2.5-flash-lite
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    google/gemma-scope-2-27b-pt/resid_post/layer_31_width_262k_l0_medium
    Prompts (Dashboard)
    392,802 prompts, 256 tokens each
    Dataset (Dashboard)
    monology/pile-uncopyrighted
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    피
    0.50
    dude
    0.50
    청
    0.50
    ້ນ
    0.49
    并没有
    0.47
    处
    0.46
    관
    0.46
    brahim
    0.45
    ta
    0.45
    ng
    0.44
    POSITIVE LOGITS
     endow
    0.55
     endowed
    0.53
     confluent
    0.52
     functors
    0.50
     ansatz
    0.50
     $\
    0.49
     distill
    0.49
     distal
    0.48
     distilling
    0.48
     moieties
    0.48
    Activations Density 0.005%

    No Known Activations