© 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-16K
    7. 12734
    Prev
    Next
    INDEX
    Explanations

    collocations with common words

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

    your physical, the slabs

    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_16k_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
    🥹
    0.59
     bespoke
    0.52
     nuanced
    0.51
     workflows
    0.50
    🥲
    0.50
    🥳
    0.50
     carers
    0.50
     digitalisation
    0.49
     robustness
    0.49
     🥰
    0.49
    POSITIVE LOGITS
    
    0.47
     touted
    0.46
    <{},
    0.43
    圄
    0.42
    كتر
    0.42
    κή
    0.42
     ২০১০
    0.42
    apeake
    0.42
     Peachtree
    0.42
     ત્રણ
    0.41
    Activations Density 0.056%

    No Known Activations