© 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. 134180
    Prev
    Next
    INDEX
    Explanations

    network structures and company growth

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

    story, survival, removal, lock

    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
    л
    0.46
    са
    0.45
    ль
    0.45
     Costs
    0.44
     controlling
    0.44
    বত
    0.44
    ك
    0.44
    рии
    0.43
    ())
    0.43
    病院
    0.43
    POSITIVE LOGITS
     التلاميذ
    0.57
     내
    0.50
    tomorrow
    0.46
     여기까지
    0.46
     üzere
    0.46
     आगामी
    0.46
     thuyền
    0.45
    제
    0.45
     அவர்களுக்கு
    0.45
     விடு
    0.44
    Activations Density 0.000%

    No Known Activations