© 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. 137825
    Prev
    Next
    INDEX
    Explanations

    popularity among, chose this, PLA entered

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

    negation, frequency, singularity

    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
    Morse
    0.47
    Cycl
    0.45
    Sous
    0.43
    ibus
    0.42
    Glasgow
    0.42
    岗
    0.41
    Esc
    0.41
     documento
    0.41
    案件
    0.41
    紳
    0.41
    POSITIVE LOGITS
     độc
    0.47
    aniyati
    0.45
     öld
    0.44
     cuk
    0.43
     donated
    0.42
     rash
    0.42
    hehi
    0.42
    тари
    0.42
     donors
    0.41
    ählt
    0.41
    Activations Density 0.001%

    No Known Activations