© 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. 247841
    Prev
    Next
    INDEX
    Explanations

    companies and financial services

    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
    nCount
    0.52
    剻
    0.46
    nout
    0.45
     pounds
    0.45
    igal
    0.45
    数目
    0.44
    㓦
    0.44
     ২০১৭
    0.43
    勹
    0.43
    bler
    0.43
    POSITIVE LOGITS
     keterampilan
    0.49
     scrumptious
    0.49
     stellt
    0.46
     kalem
    0.45
     hailing
    0.45
     direkte
    0.44
     daging
    0.44
     Commodities
    0.42
     gorgeous
    0.42
     doğrudan
    0.42
    Activations Density 0.000%

    No Known Activations