© 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
    2. Gemma-3-27B
    3. 31-GEMMASCOPE-2-RES-262K
    4. 130981
    Prev
    Next
    INDEX
    Explanations

    Security Camera

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

    acronyms and specific entities

    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
    䓶
    0.53
    砰
    0.49
     pellets
    0.48
     পানিতে
    0.46
    Hvis
    0.45
    QRect
    0.45
    Indices
    0.44
    ElementType
    0.44
    㜖
    0.44
    IR
    0.44
    POSITIVE LOGITS
     ruj
    0.60
     gwar
    0.57
     jat
    0.49
     kabul
    0.48
     inol
    0.48
     éd
    0.48
     aspiring
    0.47
     devad
    0.47
     dân
    0.47
     twor
    0.47
    Activations Density 0.001%

    No Known Activations