© 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. 126956
    Prev
    Next
    INDEX
    Explanations

    city inmain nightlifemanaging digitalnarrative paragraphs

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

    understand with targets

    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
    ność
    0.51
     providers
    0.48
     employers
    0.48
    рения
    0.48
    
    0.48
     ritmo
    0.46
    αυ
    0.46
     académicos
    0.45
     sistem
    0.45
     labourers
    0.45
    POSITIVE LOGITS
    Circular
    0.51
    iophorus
    0.47
    装着
    0.44
    xlink
    0.43
     Relig
    0.42
    "`
    0.42
     ছুটে
    0.41
     Circular
    0.41
    startswith
    0.40
    juvant
    0.40
    Activations Density 0.000%

    No Known Activations