© 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. 24563
    Prev
    Next
    INDEX
    Explanations

    copyright dates and company names

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

    positional indicators

    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
    銜
    0.44
     relev
    0.38
     حمد
    0.38
    ohex
    0.38
     preso
    0.38
     formulation
    0.37
    餾
    0.37
     considerations
    0.37
     Considerations
    0.37
    Palmer
    0.37
    POSITIVE LOGITS
    ８
    0.48
     ګرځنده
    0.46
    ９
    0.46
    ütü
    0.45
    ک
    0.45
     Over
    0.45
     امیر
    0.44
    ட்ட
    0.43
     tân
    0.42
    ോളിക
    0.42
    Activations Density 0.000%

    No Known Activations