© 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. 172787
    Prev
    Next
    INDEX
    Explanations

    registered companies

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

    compliance or conditional actions

    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
     grove
    0.42
    (!)
    0.42
    ..
    0.41
     stag
    0.41
     differ
    0.41
     magn
    0.41
     whirl
    0.41
    .=
    0.40
     tessel
    0.40
    .\
    0.40
    POSITIVE LOGITS
     Criminal
    0.46
    क्रामक
    0.45
    Relatives
    0.43
     আবারও
    0.43
     Crime
    0.42
    Alison
    0.42
    ätze
    0.39
    িপূর্ণ
    0.39
     Memories
    0.39
     Brésil
    0.39
    Activations Density 0.000%

    No Known Activations